For the goals of security and privacy preservation,we propose a blind batch encryption-and public ledger-based data sharing protocol that allows the integrity of sensitive data to be audited by a public ledger and all...For the goals of security and privacy preservation,we propose a blind batch encryption-and public ledger-based data sharing protocol that allows the integrity of sensitive data to be audited by a public ledger and allows privacy information to be preserved.Data owners can tightly manage their data with efficient revocation and only grant one-time adaptive access for the fulfillment of the requester.We prove that our protocol is semanticallly secure,blind,and secure against oblivious requesters and malicious file keepers.We also provide security analysis in the context of four typical attacks.展开更多
Autonomous driving technology has made a lot of outstanding achievements with deep learning,and the vehicle detection and classification algorithm has become one of the critical technologies of autonomous driving syst...Autonomous driving technology has made a lot of outstanding achievements with deep learning,and the vehicle detection and classification algorithm has become one of the critical technologies of autonomous driving systems.The vehicle instance segmentation can perform instance-level semantic parsing of vehicle information,which is more accurate and reliable than object detection.However,the existing instance segmentation algorithms still have the problems of poor mask prediction accuracy and low detection speed.Therefore,this paper proposes an advanced real-time instance segmentation model named FIR-YOLACT,which fuses the ICIoU(Improved Complete Intersection over Union)and Res2Net for the YOLACT algorithm.Specifically,the ICIoU function can effectively solve the degradation problem of the original CIoU loss function,and improve the training convergence speed and detection accuracy.The Res2Net module fused with the ECA(Efficient Channel Attention)Net is added to the model’s backbone network,which improves the multi-scale detection capability and mask prediction accuracy.Furthermore,the Cluster NMS(Non-Maximum Suppression)algorithm is introduced in the model’s bounding box regression to enhance the performance of detecting similarly occluded objects.The experimental results demonstrate the superiority of FIR-YOLACT to the based methods and the effectiveness of all components.The processing speed reaches 28 FPS,which meets the demands of real-time vehicle instance segmentation.展开更多
Safety helmets can reduce head injuries from object impacts and lower the probability of safety accidents,as well as being of great significance to construction safety.However,for a variety of reasons,construction wor...Safety helmets can reduce head injuries from object impacts and lower the probability of safety accidents,as well as being of great significance to construction safety.However,for a variety of reasons,construction workers nowadays may not strictly enforce the rules of wearing safety helmets.In order to strengthen the safety of construction site,the traditional practice is to manage it through methods such as regular inspections by safety officers,but the cost is high and the effect is poor.With the popularization and application of construction site video monitoring,manual video monitoring has been realized for management,but the monitors need to be on duty at all times,and thus are prone to negligence.Therefore,this study establishes a lightweight model YOLO_CA based on YOLOv5 for the automatic detection of construction workers’helmet wearing,which overcomes the shortcomings of the current manual monitoring methods that are inefficient and expensive.The coordinate attention(CA)addition to the YOLOv5 backbone strengthens detection accuracy in complex scenes by extracting critical information and suppressing non-critical information.Further parameter compression with deeply separable convolution(DWConv).In addition,to improve the feature representation speed,we swap out C3 with a Ghost module,which decreases the floating-point operations needed for feature channel fusion,and CIOU_Loss was substituted with EIOU_Loss to enhance the algorithm’s localization accuracy.Therefore,the original model needs to be improved so as to enhance the detection of safety helmets.The experimental results show that the YOLO_CA model achieves good results in all indicators compared with the mainstream model.Compared with the original model,the mAP value of the optimized model increased by 1.13%,GFLOPs cut down by 17.5%,and there is a 6.84%decrease in the total model parameters,furthermore,the weight size cuts down by 4.26%,FPS increased by 39.58%,and the detection effect and model size of this model can meet the requirements of lightweight embedding.展开更多
Due to its decentralized,tamper-proof,and trust-free characteristics,blockchain is used in the Internet of Things(IoT)to guarantee the reliability of data.However,some technical flaws in blockchain itself prevent the ...Due to its decentralized,tamper-proof,and trust-free characteristics,blockchain is used in the Internet of Things(IoT)to guarantee the reliability of data.However,some technical flaws in blockchain itself prevent the development of these applications,such as the issue with linearly growing storage capacity of blockchain systems.On the other hand,there is a lack of storage resources for sensor devices in IoT,and numerous sensor devices will generate massive data at ultra-high speed,which makes the storage problem of the IoT enabled by blockchain more prominent.There are various solutions to reduce the storage burden by modifying the blockchain’s storage policy,but most of them do not consider the willingness of peers.In attempt to make the blockchain more compatible with the IoT,this paper proposes a storage optimization scheme that revisits the system data storage problem from amore practically oriented standpoint.Peers will only store transactional data that they are directly involved in.In addition,a transaction verification model is developed to enable peers to undertake transaction verification with the aid of cloud computing,and an incentive mechanism is premised on the storage optimization scheme to assure data integrity.The results of the simulation experiments demonstrate the proposed scheme’s advantage in terms of storage and throughput.展开更多
The data in Mobile Edge Computing(MEC)contains tremendousmarket value,and data sharing canmaximize the usefulness of the data.However,certain data is quite sensitive,and sharing it directly may violate privacy.Vertica...The data in Mobile Edge Computing(MEC)contains tremendousmarket value,and data sharing canmaximize the usefulness of the data.However,certain data is quite sensitive,and sharing it directly may violate privacy.Vertical Federated Learning(VFL)is a secure distributed machine learning framework that completes joint model training by passing encryptedmodel parameters rather than raw data,so there is no data privacy leakage during the training process.Therefore,the VFL can build a bridge between data demander and owner to realize data sharing while protecting data privacy.Typically,the VFL requires a third party for key distribution and decryption of training results.In this article,we employ the consortium blockchain instead of the traditional third party and design a VFL architecture based on the consortium blockchain for data sharing in MEC.More specifically,we propose a V-Raft consensus algorithm based on Verifiable Random Functions(VRFs),which is a variant of the Raft.The VRaft is able to elect leader quickly and stably to assist data demander and owner to complete data sharing by VFL.Moreover,we apply secret sharing todistribute the private key to avoid the situationwhere the training result cannot be decrypted if the leader crashes.Finally,we analyzed the performance of the V-Raft and carried out simulation experiments,and the results show that compared with Raft,the V-Raft has higher efficiency and better scalability.展开更多
Dear Editor, In order to accommodate the effects of false data injection attacks(FDIAs), the moving target defense(MTD) strategy is recently proposed to enhance the security of the smart grid by perturbing branch susc...Dear Editor, In order to accommodate the effects of false data injection attacks(FDIAs), the moving target defense(MTD) strategy is recently proposed to enhance the security of the smart grid by perturbing branch susceptances. However, most pioneer work only focus on the defending performance of MTD in terms of detecting FDIAs and the impact of MTD on the static factors such as the power and economic losses.展开更多
Dear Editor,Machine learning(ML) approaches have been widely employed to enable real-time ML-based stability assessment(MLSA) of largescale automated electricity grids. However, the vulnerability of MLSA to malicious ...Dear Editor,Machine learning(ML) approaches have been widely employed to enable real-time ML-based stability assessment(MLSA) of largescale automated electricity grids. However, the vulnerability of MLSA to malicious cyber-attacks may lead to wrong decisions in operating the physical grid if its resilience properties are not well understood before deployment. Unlike adversarial ML in prior domains such as image processing, specific constraints of power systems that the attacker must obey in constructing adversarial samples require new research on MLSA vulnerability analysis for power systems.展开更多
Up to 2022 November,267 pulsars had been discovered in 36 globular clusters(GCs).In this paper,we present our studies on the distribution of GC pulsar parameters and the detection efficiency.The power law relation bet...Up to 2022 November,267 pulsars had been discovered in 36 globular clusters(GCs).In this paper,we present our studies on the distribution of GC pulsar parameters and the detection efficiency.The power law relation between average dispersion measure(■)and dispersion measure difference(ΔDM)of known pulsars in GCs is lgΔDM∝1.52lg■.The sensitivity could be the key to finding more pulsars.As a result,several years after the construction of a large radio telescope facility,the number of known GC pulsars will likely be increased accordingly.We suggest that currently GCs in the southern hemisphere could have higher possibilities for finding new pulsars.展开更多
Dear Editor,Dummy attack(DA), a deep stealthy but impactful data integrity attack on power industrial control processes, is recently recognized as hiding the corrupted measurements in normal measurements. In this lett...Dear Editor,Dummy attack(DA), a deep stealthy but impactful data integrity attack on power industrial control processes, is recently recognized as hiding the corrupted measurements in normal measurements. In this letter, targeting a more practical case, we aim to detect the oneshot DA, with the purpose of revealing the DA once it is launched.Specifically, we first formulate an optimization problem to generate one-shot DAs. Then, an unsupervised data-driven approach based on a modified local outlier factor(MLOF) is proposed to detect them.展开更多
The development of technologies such as big data and blockchain has brought convenience to life,but at the same time,privacy and security issues are becoming more and more prominent.The K-anonymity algorithm is an eff...The development of technologies such as big data and blockchain has brought convenience to life,but at the same time,privacy and security issues are becoming more and more prominent.The K-anonymity algorithm is an effective and low computational complexity privacy-preserving algorithm that can safeguard users’privacy by anonymizing big data.However,the algorithm currently suffers from the problem of focusing only on improving user privacy while ignoring data availability.In addition,ignoring the impact of quasi-identified attributes on sensitive attributes causes the usability of the processed data on statistical analysis to be reduced.Based on this,we propose a new K-anonymity algorithm to solve the privacy security problem in the context of big data,while guaranteeing improved data usability.Specifically,we construct a new information loss function based on the information quantity theory.Considering that different quasi-identification attributes have different impacts on sensitive attributes,we set weights for each quasi-identification attribute when designing the information loss function.In addition,to reduce information loss,we improve K-anonymity in two ways.First,we make the loss of information smaller than in the original table while guaranteeing privacy based on common artificial intelligence algorithms,i.e.,greedy algorithm and 2-means clustering algorithm.In addition,we improve the 2-means clustering algorithm by designing a mean-center method to select the initial center of mass.Meanwhile,we design the K-anonymity algorithm of this scheme based on the constructed information loss function,the improved 2-means clustering algorithm,and the greedy algorithm,which reduces the information loss.Finally,we experimentally demonstrate the effectiveness of the algorithm in improving the effect of 2-means clustering and reducing information loss.展开更多
Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test sample.It has been widely used in various image classification tasks.Sparseness in ...Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test sample.It has been widely used in various image classification tasks.Sparseness in sparse representation means that only a few of instances selected from all training samples can effectively convey the essential class-specific information of the test sample,which is very important for classification.For deformable images such as human faces,pixels at the same location of different images of the same subject usually have different intensities.Therefore,extracting features and correctly classifying such deformable objects is very hard.Moreover,the lighting,attitude and occlusion cause more difficulty.Considering the problems and challenges listed above,a novel image representation and classification algorithm is proposed.First,the authors’algorithm generates virtual samples by a non-linear variation method.This method can effectively extract the low-frequency information of space-domain features of the original image,which is very useful for representing deformable objects.The combination of the original and virtual samples is more beneficial to improve the clas-sification performance and robustness of the algorithm.Thereby,the authors’algorithm calculates the expression coefficients of the original and virtual samples separately using the sparse representation principle and obtains the final score by a designed efficient score fusion scheme.The weighting coefficients in the score fusion scheme are set entirely automatically.Finally,the algorithm classifies the samples based on the final scores.The experimental results show that our method performs better classification than conventional sparse representation algorithms.展开更多
In the assessment of car insurance claims,the claim rate for car insurance presents a highly skewed probability distribution,which is typically modeled using Tweedie distribution.The traditional approach to obtaining ...In the assessment of car insurance claims,the claim rate for car insurance presents a highly skewed probability distribution,which is typically modeled using Tweedie distribution.The traditional approach to obtaining the Tweedie regression model involves training on a centralized dataset,when the data is provided by multiple parties,training a privacy-preserving Tweedie regression model without exchanging raw data becomes a challenge.To address this issue,this study introduces a novel vertical federated learning-based Tweedie regression algorithm for multi-party auto insurance rate setting in data silos.The algorithm can keep sensitive data locally and uses privacy-preserving techniques to achieve intersection operations between the two parties holding the data.After determining which entities are shared,the participants train the model locally using the shared entity data to obtain the local generalized linear model intermediate parameters.The homomorphic encryption algorithms are introduced to interact with and update the model intermediate parameters to collaboratively complete the joint training of the car insurance rate-setting model.Performance tests on two publicly available datasets show that the proposed federated Tweedie regression algorithm can effectively generate Tweedie regression models that leverage the value of data fromboth partieswithout exchanging data.The assessment results of the scheme approach those of the Tweedie regressionmodel learned fromcentralized data,and outperformthe Tweedie regressionmodel learned independently by a single party.展开更多
Cloud-based services have powerful storage functions and can provide accurate computation.However,the question of how to guarantee cloud-based services access control and achieve data sharing security has always been ...Cloud-based services have powerful storage functions and can provide accurate computation.However,the question of how to guarantee cloud-based services access control and achieve data sharing security has always been a research highlight.Although the attribute-based proxy re-encryption(ABPRE)schemes based on number theory can solve this problem,it is still difficult to resist quantum attacks and have limited expression capabilities.To address these issues,we present a novel linear secret sharing schemes(LSSS)matrix-based ABPRE scheme with the fine-grained policy on the lattice in the research.Additionally,to detect the activities of illegal proxies,homomorphic signature(HS)technology is introduced to realize the verifiability of re-encryption.Moreover,the non-interactivity,unidirectionality,proxy transparency,multi-use,and anti-quantum attack characteristics of our system are all advantageous.Besides,it can efficiently prevent the loss of processing power brought on by repetitive authorisation and can enable precise and safe data sharing in the cloud.Furthermore,under the standard model,the proposed learning with errors(LWE)-based scheme was proven to be IND-sCPA secure.展开更多
With the emergence of classical communication security problems,quantum communication has been studied more extensively.In this paper,a novel probabilistic hierarchical quantum information splitting protocol is design...With the emergence of classical communication security problems,quantum communication has been studied more extensively.In this paper,a novel probabilistic hierarchical quantum information splitting protocol is designed by using a non-maximally entangled four-qubit cluster state.Firstly,the sender Alice splits and teleports an arbitrary one-qubit secret state invisibly to three remote agents Bob,Charlie,and David.One agent David is in high grade,the other two agents Bob and Charlie are in low grade.Secondly,the receiver in high grade needs the assistance of one agent in low grade,while the receiver in low grade needs the aid of all agents.While introducing an ancillary qubit,the receiver’s state can be inferred from the POVM measurement result of the ancillary qubit.Finally,with the help of other agents,the receiver can recover the secret state probabilistically by performing certain unitary operation on his own qubit.In addition,the security of the protocol under eavesdropping attacks is analyzed.In this proposed protocol,the agents need only single-qubit measurements to achieve probabilistic hierarchical quantum information splitting,which has appealing advantages in actual experiments.Such a probabilistic hierarchical quantum information splitting protocol hierarchical is expected to be more practical in multipartite quantum cryptography.展开更多
Anomaly detection is crucial to the flight safety and maintenance of unmanned aerial vehicles(UAVs)and has attracted extensive attention from scholars.Knowledge-based approaches rely on prior knowledge,while model-bas...Anomaly detection is crucial to the flight safety and maintenance of unmanned aerial vehicles(UAVs)and has attracted extensive attention from scholars.Knowledge-based approaches rely on prior knowledge,while model-based approaches are challenging for constructing accurate and complex physical models of unmanned aerial systems(UASs).Although data-driven methods do not require extensive prior knowledge and accurate physical UAS models,they often lack parameter selection and are limited by the cost of labeling anomalous data.Furthermore,flight data with random noise pose a significant challenge for anomaly detection.This work proposes a spatiotemporal correlation based on long short-term memory and autoencoder(STCLSTM-AE)neural network data-driven method for unsupervised anomaly detection and recovery of UAV flight data.First,UAV flight data are preprocessed by combining the Savitzky-Golay filter data processing technique to mitigate the effect of noise in the original historical flight data on the model.Correlation-based feature subset selection is subsequently performed to reduce the reliance on expert knowledge.Then,the extracted features are used as the input of the designed LSTM-AE model to achieve the anomaly detection and recovery of UAV flight data in an unsupervised manner.Finally,the method's effectiveness is validated on real UAV flight data.展开更多
Flight data anomaly detection plays an imperative role in the safety and maintenance of unmanned aerial vehicles(UAVs).It has attracted extensive attention from researchers.However,the problems related to the difficul...Flight data anomaly detection plays an imperative role in the safety and maintenance of unmanned aerial vehicles(UAVs).It has attracted extensive attention from researchers.However,the problems related to the difficulty in obtaining abnormal data,low model accuracy,and high calculation cost have led to severe challenges with respect to its practical applications.Hence,in this study,firstly,several UAV flight data simulation softwares are presented based on a brief presentation of the basic concepts of anomalies,the contents of UAV flight data,and the public datasets for flight data anomaly detection.Then,anomaly detection technologies for UAV flight data are comprehensively reviewed,including knowledge-based,model-based,and data-driven methods.Next,UAV flight data anomaly detection applications are briefly described and analyzed.Finally,the future trends and directions of UAV flight data anomaly detection are summarized and prospected,which aims to provide references for the following research.展开更多
With the development of cloud computing technology,more and more data owners upload their local data to the public cloud server for storage and calculation.While this can save customers’operating costs,it also poses ...With the development of cloud computing technology,more and more data owners upload their local data to the public cloud server for storage and calculation.While this can save customers’operating costs,it also poses privacy and security challenges.Such challenges can be solved using secure multi-party computation(SMPC),but this still exposes more security issues.In cloud computing using SMPC,clients need to process their data and submit the processed data to the cloud server,which then performs the calculation and returns the results to each client.Each client and server must be honest.If there is cooperation or dishonest behavior between clients,some clients may profit from it or even disclose the private data of other clients.This paper proposes the SMPC based on a Partially-Homomorphic Encryption(PHE)scheme in which an addition homomorphic encryption algorithm with a lower computational cost is used to ensure data comparability and Zero-Knowledge Proof(ZKP)is used to limit the client’s malicious behavior.In addition,the introduction of Oblivious Transfer(OT)technology also ensures that the semi-honest cloud server knows nothing about private data,so that the cloud server of this scheme can calculate the correct data in the case of malicious participant models and safely return the calculation results to each client.Finally,the security analysis shows that the scheme not only ensures the privacy of participants,but also ensures the fairness of the comparison protocol data.展开更多
Federated learning is a widely used distributed learning approach in recent years,however,despite model training from collecting data become to gathering parameters,privacy violations may occur when publishing and sha...Federated learning is a widely used distributed learning approach in recent years,however,despite model training from collecting data become to gathering parameters,privacy violations may occur when publishing and sharing models.A dynamic approach is pro-posed to add Gaussian noise more effectively and apply differential privacy to federal deep learning.Concretely,it is abandoning the traditional way of equally distributing the privacy budget e and adjusting the privacy budget to accommodate gradient descent federation learning dynamically,where the parameters depend on computation derived to avoid the impact on the algorithm that hyperparameters are created manually.It also incorporates adaptive threshold cropping to control the sensitivity,and finally,moments accountant is used to counting the∈consumed on the privacy‐preserving,and learning is stopped only if the∈_(total)by clients setting is reached,this allows the privacy budget to be adequately explored for model training.The experimental results on real datasets show that the method training has almost the same effect as the model learning of non‐privacy,which is significantly better than the differential privacy method used by TensorFlow.展开更多
Fe-Mn-C-Al alloys have been recognized as promising materials for certain low-temperature applications due to their exceptional mechanical properties and cost-effectiveness.However,their limited low-temperature toughn...Fe-Mn-C-Al alloys have been recognized as promising materials for certain low-temperature applications due to their exceptional mechanical properties and cost-effectiveness.However,their limited low-temperature toughness restricts their large-scale applications in specific scenarios.The influence of trace amounts of rare earth cerium(Ce)on the low-temperature toughness of Fe-18Mn-0.6C-1.8Al alloys was investigated.The addition of Ce effectively alters the inclu-sions in the alloy,transforming large-sized irregular inclusions into fine ellipsoidal rare earth inclusions.This leads to a significant reduction in both the proportion and average size of the inclusions,resulting in their effective dispersion throughout the matrix and improved cryogenic performance.The presence of Ce-containing inclusions within the matrix reduces stress concentration,thereby inhibiting microcrack formation and improving impact absorption energy.Specifi-cally,the addition of rare earth Ce alters the fracture behavior of the material at room temperature and low temperature,changing from brittle cleavage fracture to a more ductile failure mode.The impact toughness of the Fe-Mn-C-Al alloy is significantly improved by the addition of 0.0048 wt.%Ce,particularly at-196℃where the impact toughness reaches 103.6 J/cm^(2),representing an impressive improvement of 87.3%.展开更多
Traditional blockchain key management schemes store private keys in the same location,which can easily lead to security issues such as a single point of failure.Therefore,decentralized threshold key management schemes...Traditional blockchain key management schemes store private keys in the same location,which can easily lead to security issues such as a single point of failure.Therefore,decentralized threshold key management schemes have become a research focus for blockchain private key protection.The security of private keys for blockchain user wallet is highly related to user identity authentication and digital asset security.The threshold blockchain private key management schemes based on verifiable secret sharing have made some progress,but these schemes do not consider participants’self-interested behavior,and require trusted nodes to keep private key fragments,resulting in a narrow application scope and low deployment efficiency,which cannot meet the needs of personal wallet private key escrow and recovery in public blockchains.We design a private key management scheme based on rational secret sharing that considers the self-interest of participants in secret sharing protocols,and constrains the behavior of rational participants through reasonable mechanism design,making it more suitable in distributed scenarios such as the public blockchain.The proposed scheme achieves the escrow and recovery of personal wallet private keys without the participation of trusted nodes,and simulate its implementation on smart contracts.Compared to other existing threshold wallet solutions and keymanagement schemes based on password-protected secret sharing(PPSS),the proposed scheme has a wide range of applications,verifiable private key recovery,low communication overhead,higher computational efficiency when users perform one-time multi-key escrow,no need for trusted nodes,and personal rational constraints and anti-collusion attack capabilities.展开更多
基金partially supported by the National Natural Science Foundation of China under grant no.62372245the Foundation of Yunnan Key Laboratory of Blockchain Application Technology under Grant 202105AG070005+1 种基金in part by the Foundation of State Key Laboratory of Public Big Datain part by the Foundation of Key Laboratory of Computational Science and Application of Hainan Province under Grant JSKX202202。
文摘For the goals of security and privacy preservation,we propose a blind batch encryption-and public ledger-based data sharing protocol that allows the integrity of sensitive data to be audited by a public ledger and allows privacy information to be preserved.Data owners can tightly manage their data with efficient revocation and only grant one-time adaptive access for the fulfillment of the requester.We prove that our protocol is semanticallly secure,blind,and secure against oblivious requesters and malicious file keepers.We also provide security analysis in the context of four typical attacks.
基金supported by the Natural Science Foundation of Guizhou Province(Grant Number:20161054)Joint Natural Science Foundation of Guizhou Province(Grant Number:LH20177226)+1 种基金2017 Special Project of New Academic Talent Training and Innovation Exploration of Guizhou University(Grant Number:20175788)The National Natural Science Foundation of China under Grant No.12205062.
文摘Autonomous driving technology has made a lot of outstanding achievements with deep learning,and the vehicle detection and classification algorithm has become one of the critical technologies of autonomous driving systems.The vehicle instance segmentation can perform instance-level semantic parsing of vehicle information,which is more accurate and reliable than object detection.However,the existing instance segmentation algorithms still have the problems of poor mask prediction accuracy and low detection speed.Therefore,this paper proposes an advanced real-time instance segmentation model named FIR-YOLACT,which fuses the ICIoU(Improved Complete Intersection over Union)and Res2Net for the YOLACT algorithm.Specifically,the ICIoU function can effectively solve the degradation problem of the original CIoU loss function,and improve the training convergence speed and detection accuracy.The Res2Net module fused with the ECA(Efficient Channel Attention)Net is added to the model’s backbone network,which improves the multi-scale detection capability and mask prediction accuracy.Furthermore,the Cluster NMS(Non-Maximum Suppression)algorithm is introduced in the model’s bounding box regression to enhance the performance of detecting similarly occluded objects.The experimental results demonstrate the superiority of FIR-YOLACT to the based methods and the effectiveness of all components.The processing speed reaches 28 FPS,which meets the demands of real-time vehicle instance segmentation.
基金funded by Guizhou Optoelectronic Information and Intelligent Application International Joint Research Center(Qiankehe Platform Talents No.5802[2019]).
文摘Safety helmets can reduce head injuries from object impacts and lower the probability of safety accidents,as well as being of great significance to construction safety.However,for a variety of reasons,construction workers nowadays may not strictly enforce the rules of wearing safety helmets.In order to strengthen the safety of construction site,the traditional practice is to manage it through methods such as regular inspections by safety officers,but the cost is high and the effect is poor.With the popularization and application of construction site video monitoring,manual video monitoring has been realized for management,but the monitors need to be on duty at all times,and thus are prone to negligence.Therefore,this study establishes a lightweight model YOLO_CA based on YOLOv5 for the automatic detection of construction workers’helmet wearing,which overcomes the shortcomings of the current manual monitoring methods that are inefficient and expensive.The coordinate attention(CA)addition to the YOLOv5 backbone strengthens detection accuracy in complex scenes by extracting critical information and suppressing non-critical information.Further parameter compression with deeply separable convolution(DWConv).In addition,to improve the feature representation speed,we swap out C3 with a Ghost module,which decreases the floating-point operations needed for feature channel fusion,and CIOU_Loss was substituted with EIOU_Loss to enhance the algorithm’s localization accuracy.Therefore,the original model needs to be improved so as to enhance the detection of safety helmets.The experimental results show that the YOLO_CA model achieves good results in all indicators compared with the mainstream model.Compared with the original model,the mAP value of the optimized model increased by 1.13%,GFLOPs cut down by 17.5%,and there is a 6.84%decrease in the total model parameters,furthermore,the weight size cuts down by 4.26%,FPS increased by 39.58%,and the detection effect and model size of this model can meet the requirements of lightweight embedding.
基金We would also thank the support from the National Natural Science Foundation of China(Nos.62172182,62202118,61962009)the Top Technology Talent Project from Guizhou Education Department(Qian jiao ji[2022]073)The Opening Foundation of Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province(Grant No.ZNKZN2021-07).
文摘Due to its decentralized,tamper-proof,and trust-free characteristics,blockchain is used in the Internet of Things(IoT)to guarantee the reliability of data.However,some technical flaws in blockchain itself prevent the development of these applications,such as the issue with linearly growing storage capacity of blockchain systems.On the other hand,there is a lack of storage resources for sensor devices in IoT,and numerous sensor devices will generate massive data at ultra-high speed,which makes the storage problem of the IoT enabled by blockchain more prominent.There are various solutions to reduce the storage burden by modifying the blockchain’s storage policy,but most of them do not consider the willingness of peers.In attempt to make the blockchain more compatible with the IoT,this paper proposes a storage optimization scheme that revisits the system data storage problem from amore practically oriented standpoint.Peers will only store transactional data that they are directly involved in.In addition,a transaction verification model is developed to enable peers to undertake transaction verification with the aid of cloud computing,and an incentive mechanism is premised on the storage optimization scheme to assure data integrity.The results of the simulation experiments demonstrate the proposed scheme’s advantage in terms of storage and throughput.
基金funded by the National Natural Science Foundation(61962009)the National Natural Science Foundation(62202118)+1 种基金Top Technology Talent Project from Guizhou Education Department(Qianjiao ji[2022]073)Foundation of Guangxi Key Laboratory of Cryptography and Information Security(GCIS202118).
文摘The data in Mobile Edge Computing(MEC)contains tremendousmarket value,and data sharing canmaximize the usefulness of the data.However,certain data is quite sensitive,and sharing it directly may violate privacy.Vertical Federated Learning(VFL)is a secure distributed machine learning framework that completes joint model training by passing encryptedmodel parameters rather than raw data,so there is no data privacy leakage during the training process.Therefore,the VFL can build a bridge between data demander and owner to realize data sharing while protecting data privacy.Typically,the VFL requires a third party for key distribution and decryption of training results.In this article,we employ the consortium blockchain instead of the traditional third party and design a VFL architecture based on the consortium blockchain for data sharing in MEC.More specifically,we propose a V-Raft consensus algorithm based on Verifiable Random Functions(VRFs),which is a variant of the Raft.The VRaft is able to elect leader quickly and stably to assist data demander and owner to complete data sharing by VFL.Moreover,we apply secret sharing todistribute the private key to avoid the situationwhere the training result cannot be decrypted if the leader crashes.Finally,we analyzed the performance of the V-Raft and carried out simulation experiments,and the results show that compared with Raft,the V-Raft has higher efficiency and better scalability.
基金supported in part by the Guizhou Provincial Science and Technology Projects(ZK[2022]149)the Natural Science Foundation of Guizhou University([2021]47)+4 种基金the GZU Cultivation project of the National Natural Science Foundation of China(NSFC)([2020]80)NSFC(62073285,62061130220)the Natural Science Foundation of Zhejiang Province(LZ21F 020006)the Fundamental Research Funds for the Central Universities(226-2022-00120)the Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province。
文摘Dear Editor, In order to accommodate the effects of false data injection attacks(FDIAs), the moving target defense(MTD) strategy is recently proposed to enhance the security of the smart grid by perturbing branch susceptances. However, most pioneer work only focus on the defending performance of MTD in terms of detecting FDIAs and the impact of MTD on the static factors such as the power and economic losses.
基金supported in part by the Guizhou Provincial Science and Technology Projects(ZK[2022]149)the Special Foundation of Guizhou University(GZU)([2021]47)+2 种基金the Guizhou Provincial Research Project for Universities([2022]104)the GZU cultivation project of the National Natural Science Foundation of China([2020]80)Shanghai Engineering Research Center of Big Data Management。
文摘Dear Editor,Machine learning(ML) approaches have been widely employed to enable real-time ML-based stability assessment(MLSA) of largescale automated electricity grids. However, the vulnerability of MLSA to malicious cyber-attacks may lead to wrong decisions in operating the physical grid if its resilience properties are not well understood before deployment. Unlike adversarial ML in prior domains such as image processing, specific constraints of power systems that the attacker must obey in constructing adversarial samples require new research on MLSA vulnerability analysis for power systems.
基金supported by the National SKA Program of China No.2020SKA0120100the National Natural Science Foundation of China(NSFC,Grant Nos.11963002,11703047,11773041,U2031119,12173052,12003047 and 12173053)+7 种基金the fostering project of Guizhou University with No.201911Cultivation Project for FAST Scientific Payoff and Research Achievement of CAMS-CASsupported by the Specialized Research Fund for State Key Laboratoriessupported by the CAS“Light of West China”Programthe Youth Innovation Promotion Association of CAS(id 2023064)supported by the Youth Innovation Promotion Association of CAS(id.2018075 and Y2022027)supported by Guizhou Provincial Basic Research Program(Natural Science)(ZK[2023]039)Key Technology R&D Program([2023]352)。
文摘Up to 2022 November,267 pulsars had been discovered in 36 globular clusters(GCs).In this paper,we present our studies on the distribution of GC pulsar parameters and the detection efficiency.The power law relation between average dispersion measure(■)and dispersion measure difference(ΔDM)of known pulsars in GCs is lgΔDM∝1.52lg■.The sensitivity could be the key to finding more pulsars.As a result,several years after the construction of a large radio telescope facility,the number of known GC pulsars will likely be increased accordingly.We suggest that currently GCs in the southern hemisphere could have higher possibilities for finding new pulsars.
基金supported in part by the Guizhou Provincial Science and Technology Projects(ZK[2022]149)the Guizhou Provincial Research Project for Universities([2022]104)+2 种基金the Special Foundation of Guizhou University([2021]47)the GZU cultivation project of National Natural Science Foundation of China([2020]80)Shanghai Engineering Research Center of Big Data Management,and the National Natural Science Foundation of China(62073285,62061130220)。
文摘Dear Editor,Dummy attack(DA), a deep stealthy but impactful data integrity attack on power industrial control processes, is recently recognized as hiding the corrupted measurements in normal measurements. In this letter, targeting a more practical case, we aim to detect the oneshot DA, with the purpose of revealing the DA once it is launched.Specifically, we first formulate an optimization problem to generate one-shot DAs. Then, an unsupervised data-driven approach based on a modified local outlier factor(MLOF) is proposed to detect them.
基金Foundation of National Natural Science Foundation of China(62202118)Scientific and Technological Research Projects from Guizhou Education Department([2023]003)+1 种基金Guizhou Provincial Department of Science and Technology Hundred Levels of Innovative Talents Project(GCC[2023]018)Top Technology Talent Project from Guizhou Education Department([2022]073).
文摘The development of technologies such as big data and blockchain has brought convenience to life,but at the same time,privacy and security issues are becoming more and more prominent.The K-anonymity algorithm is an effective and low computational complexity privacy-preserving algorithm that can safeguard users’privacy by anonymizing big data.However,the algorithm currently suffers from the problem of focusing only on improving user privacy while ignoring data availability.In addition,ignoring the impact of quasi-identified attributes on sensitive attributes causes the usability of the processed data on statistical analysis to be reduced.Based on this,we propose a new K-anonymity algorithm to solve the privacy security problem in the context of big data,while guaranteeing improved data usability.Specifically,we construct a new information loss function based on the information quantity theory.Considering that different quasi-identification attributes have different impacts on sensitive attributes,we set weights for each quasi-identification attribute when designing the information loss function.In addition,to reduce information loss,we improve K-anonymity in two ways.First,we make the loss of information smaller than in the original table while guaranteeing privacy based on common artificial intelligence algorithms,i.e.,greedy algorithm and 2-means clustering algorithm.In addition,we improve the 2-means clustering algorithm by designing a mean-center method to select the initial center of mass.Meanwhile,we design the K-anonymity algorithm of this scheme based on the constructed information loss function,the improved 2-means clustering algorithm,and the greedy algorithm,which reduces the information loss.Finally,we experimentally demonstrate the effectiveness of the algorithm in improving the effect of 2-means clustering and reducing information loss.
文摘Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test sample.It has been widely used in various image classification tasks.Sparseness in sparse representation means that only a few of instances selected from all training samples can effectively convey the essential class-specific information of the test sample,which is very important for classification.For deformable images such as human faces,pixels at the same location of different images of the same subject usually have different intensities.Therefore,extracting features and correctly classifying such deformable objects is very hard.Moreover,the lighting,attitude and occlusion cause more difficulty.Considering the problems and challenges listed above,a novel image representation and classification algorithm is proposed.First,the authors’algorithm generates virtual samples by a non-linear variation method.This method can effectively extract the low-frequency information of space-domain features of the original image,which is very useful for representing deformable objects.The combination of the original and virtual samples is more beneficial to improve the clas-sification performance and robustness of the algorithm.Thereby,the authors’algorithm calculates the expression coefficients of the original and virtual samples separately using the sparse representation principle and obtains the final score by a designed efficient score fusion scheme.The weighting coefficients in the score fusion scheme are set entirely automatically.Finally,the algorithm classifies the samples based on the final scores.The experimental results show that our method performs better classification than conventional sparse representation algorithms.
基金This research was funded by the National Natural Science Foundation of China(No.62272124)the National Key Research and Development Program of China(No.2022YFB2701401)+3 种基金Guizhou Province Science and Technology Plan Project(Grant Nos.Qiankehe Paltform Talent[2020]5017)The Research Project of Guizhou University for Talent Introduction(No.[2020]61)the Cultivation Project of Guizhou University(No.[2019]56)the Open Fund of Key Laboratory of Advanced Manufacturing Technology,Ministry of Education(GZUAMT2021KF[01]).
文摘In the assessment of car insurance claims,the claim rate for car insurance presents a highly skewed probability distribution,which is typically modeled using Tweedie distribution.The traditional approach to obtaining the Tweedie regression model involves training on a centralized dataset,when the data is provided by multiple parties,training a privacy-preserving Tweedie regression model without exchanging raw data becomes a challenge.To address this issue,this study introduces a novel vertical federated learning-based Tweedie regression algorithm for multi-party auto insurance rate setting in data silos.The algorithm can keep sensitive data locally and uses privacy-preserving techniques to achieve intersection operations between the two parties holding the data.After determining which entities are shared,the participants train the model locally using the shared entity data to obtain the local generalized linear model intermediate parameters.The homomorphic encryption algorithms are introduced to interact with and update the model intermediate parameters to collaboratively complete the joint training of the car insurance rate-setting model.Performance tests on two publicly available datasets show that the proposed federated Tweedie regression algorithm can effectively generate Tweedie regression models that leverage the value of data fromboth partieswithout exchanging data.The assessment results of the scheme approach those of the Tweedie regressionmodel learned fromcentralized data,and outperformthe Tweedie regressionmodel learned independently by a single party.
基金The project is provided funding by the Natural Science Foundation of China(Nos.62272124,2022YFB2701400)the Science and Technology Program of Guizhou Province(No.[2020]5017)+3 种基金the Research Project of Guizhou University for Talent Introduction(No.[2020]61)the Cultivation Project of Guizhou University(No.[2019]56)the Open Fund of Key Laboratory of Advanced Manufacturing Technology,Ministry of Education,GZUAMT2021KF[01]the Postgraduate Innovation Program in Guizhou Province(No.YJSKYJJ[2021]028).
文摘Cloud-based services have powerful storage functions and can provide accurate computation.However,the question of how to guarantee cloud-based services access control and achieve data sharing security has always been a research highlight.Although the attribute-based proxy re-encryption(ABPRE)schemes based on number theory can solve this problem,it is still difficult to resist quantum attacks and have limited expression capabilities.To address these issues,we present a novel linear secret sharing schemes(LSSS)matrix-based ABPRE scheme with the fine-grained policy on the lattice in the research.Additionally,to detect the activities of illegal proxies,homomorphic signature(HS)technology is introduced to realize the verifiability of re-encryption.Moreover,the non-interactivity,unidirectionality,proxy transparency,multi-use,and anti-quantum attack characteristics of our system are all advantageous.Besides,it can efficiently prevent the loss of processing power brought on by repetitive authorisation and can enable precise and safe data sharing in the cloud.Furthermore,under the standard model,the proposed learning with errors(LWE)-based scheme was proven to be IND-sCPA secure.
基金This work is supported by the NSFC(Grant Nos.92046001,61571024,61671087,61962009,61971021)the Open Foundation of Guizhou Provincial Key Laboratory of Public Big Data(Grant Nos.2018BDKFJJ018,2019BDKFJJ010,2019BDKFJJ014)+5 种基金the Open Research Project of the State Key Laboratory of Media Convergence and Communication,Communication University of China,China(Grant No.SKLMCC2020KF006)the High-quality and Cutting-edge Disciplines Construction Project for Universities in Beijing(Internet Information,Communication University of China)the Fundamental Research Funds for the Central Universities(Grant No.2019XD-A02)the Scientific Research Foundation of North China University of Technologythe Fundamental Research Funds for the Beijing Municipal Education CommissionJSPS KAKENHI Grant Number JP20F20080.
文摘With the emergence of classical communication security problems,quantum communication has been studied more extensively.In this paper,a novel probabilistic hierarchical quantum information splitting protocol is designed by using a non-maximally entangled four-qubit cluster state.Firstly,the sender Alice splits and teleports an arbitrary one-qubit secret state invisibly to three remote agents Bob,Charlie,and David.One agent David is in high grade,the other two agents Bob and Charlie are in low grade.Secondly,the receiver in high grade needs the assistance of one agent in low grade,while the receiver in low grade needs the aid of all agents.While introducing an ancillary qubit,the receiver’s state can be inferred from the POVM measurement result of the ancillary qubit.Finally,with the help of other agents,the receiver can recover the secret state probabilistically by performing certain unitary operation on his own qubit.In addition,the security of the protocol under eavesdropping attacks is analyzed.In this proposed protocol,the agents need only single-qubit measurements to achieve probabilistic hierarchical quantum information splitting,which has appealing advantages in actual experiments.Such a probabilistic hierarchical quantum information splitting protocol hierarchical is expected to be more practical in multipartite quantum cryptography.
基金supported by the National Key Research and Development Program of China(Grant No.2020YFB1713300)the Guizhou Provincial Colleges and Universities Talent Training Base Project(Grant No.[2020]009)+3 种基金the Guizhou Province Science and Technology Plan Project(Grant Nos.[2015]4011,[2017]5788)the Guizhou Provincial Department of Education Youth Science and Technology Talent Growth Project(Grant No.[2022]142)the Scientific Research Project for Introducing Talents from Guizhou University(Grant No.(2021)74)the Guizhou Province Higher Education Integrated Research Platform Project(Grant No.[2020]005)。
文摘Anomaly detection is crucial to the flight safety and maintenance of unmanned aerial vehicles(UAVs)and has attracted extensive attention from scholars.Knowledge-based approaches rely on prior knowledge,while model-based approaches are challenging for constructing accurate and complex physical models of unmanned aerial systems(UASs).Although data-driven methods do not require extensive prior knowledge and accurate physical UAS models,they often lack parameter selection and are limited by the cost of labeling anomalous data.Furthermore,flight data with random noise pose a significant challenge for anomaly detection.This work proposes a spatiotemporal correlation based on long short-term memory and autoencoder(STCLSTM-AE)neural network data-driven method for unsupervised anomaly detection and recovery of UAV flight data.First,UAV flight data are preprocessed by combining the Savitzky-Golay filter data processing technique to mitigate the effect of noise in the original historical flight data on the model.Correlation-based feature subset selection is subsequently performed to reduce the reliance on expert knowledge.Then,the extracted features are used as the input of the designed LSTM-AE model to achieve the anomaly detection and recovery of UAV flight data in an unsupervised manner.Finally,the method's effectiveness is validated on real UAV flight data.
基金supported by the National Key R&D Program of China(Grant No.2020YFB1713300)Guizhou Provincial Colleges and Universities Talent Training Base Project(Grant No.[2020]009)+3 种基金Guizhou Province Science and Technology Plan Project(Grant Nos.[2015]4011 and[2017]5788)Guizhou Provincial Department of Education Youth Science and Technology Talent Growth Project(Grant No.[2022]142)the Scientific Research Project for Introducing Talents from Guizhou University(Grant No.(2021)74)the Guizhou Province Higher Education Integrated Research Platform Project(Grant No.[2020]005)。
文摘Flight data anomaly detection plays an imperative role in the safety and maintenance of unmanned aerial vehicles(UAVs).It has attracted extensive attention from researchers.However,the problems related to the difficulty in obtaining abnormal data,low model accuracy,and high calculation cost have led to severe challenges with respect to its practical applications.Hence,in this study,firstly,several UAV flight data simulation softwares are presented based on a brief presentation of the basic concepts of anomalies,the contents of UAV flight data,and the public datasets for flight data anomaly detection.Then,anomaly detection technologies for UAV flight data are comprehensively reviewed,including knowledge-based,model-based,and data-driven methods.Next,UAV flight data anomaly detection applications are briefly described and analyzed.Finally,the future trends and directions of UAV flight data anomaly detection are summarized and prospected,which aims to provide references for the following research.
基金supported by the National Natural Science Foundation of China under Grant No.(62202118.61962009)And in part by Natural Science Foundation of Shandong Province(ZR2021MF086)+1 种基金And in part by Top Technology Talent Project from Guizhou Education Department(Qian jiao ji[2022]073)And in part by Foundation of Guangxi Key Laboratory of Cryptography and Information Security(GCIS202118).
文摘With the development of cloud computing technology,more and more data owners upload their local data to the public cloud server for storage and calculation.While this can save customers’operating costs,it also poses privacy and security challenges.Such challenges can be solved using secure multi-party computation(SMPC),but this still exposes more security issues.In cloud computing using SMPC,clients need to process their data and submit the processed data to the cloud server,which then performs the calculation and returns the results to each client.Each client and server must be honest.If there is cooperation or dishonest behavior between clients,some clients may profit from it or even disclose the private data of other clients.This paper proposes the SMPC based on a Partially-Homomorphic Encryption(PHE)scheme in which an addition homomorphic encryption algorithm with a lower computational cost is used to ensure data comparability and Zero-Knowledge Proof(ZKP)is used to limit the client’s malicious behavior.In addition,the introduction of Oblivious Transfer(OT)technology also ensures that the semi-honest cloud server knows nothing about private data,so that the cloud server of this scheme can calculate the correct data in the case of malicious participant models and safely return the calculation results to each client.Finally,the security analysis shows that the scheme not only ensures the privacy of participants,but also ensures the fairness of the comparison protocol data.
基金supported by the National Natural Science Foundation of China under Grant No.62062020 and No.72161005,NO.62002081,NO.62062017Technology Founda-tion of Guizhou Province(grant no.QianKeHeJiChu‐ZK[2022]‐General184)Guizhou Provincial Science and Technology Projects[2020]1Y265.
文摘Federated learning is a widely used distributed learning approach in recent years,however,despite model training from collecting data become to gathering parameters,privacy violations may occur when publishing and sharing models.A dynamic approach is pro-posed to add Gaussian noise more effectively and apply differential privacy to federal deep learning.Concretely,it is abandoning the traditional way of equally distributing the privacy budget e and adjusting the privacy budget to accommodate gradient descent federation learning dynamically,where the parameters depend on computation derived to avoid the impact on the algorithm that hyperparameters are created manually.It also incorporates adaptive threshold cropping to control the sensitivity,and finally,moments accountant is used to counting the∈consumed on the privacy‐preserving,and learning is stopped only if the∈_(total)by clients setting is reached,this allows the privacy budget to be adequately explored for model training.The experimental results on real datasets show that the method training has almost the same effect as the model learning of non‐privacy,which is significantly better than the differential privacy method used by TensorFlow.
基金This work was supported by the National Natural Science Foundation of China(No.52164032)the Hong Kong Scholars Program(2021-077).
文摘Fe-Mn-C-Al alloys have been recognized as promising materials for certain low-temperature applications due to their exceptional mechanical properties and cost-effectiveness.However,their limited low-temperature toughness restricts their large-scale applications in specific scenarios.The influence of trace amounts of rare earth cerium(Ce)on the low-temperature toughness of Fe-18Mn-0.6C-1.8Al alloys was investigated.The addition of Ce effectively alters the inclu-sions in the alloy,transforming large-sized irregular inclusions into fine ellipsoidal rare earth inclusions.This leads to a significant reduction in both the proportion and average size of the inclusions,resulting in their effective dispersion throughout the matrix and improved cryogenic performance.The presence of Ce-containing inclusions within the matrix reduces stress concentration,thereby inhibiting microcrack formation and improving impact absorption energy.Specifi-cally,the addition of rare earth Ce alters the fracture behavior of the material at room temperature and low temperature,changing from brittle cleavage fracture to a more ductile failure mode.The impact toughness of the Fe-Mn-C-Al alloy is significantly improved by the addition of 0.0048 wt.%Ce,particularly at-196℃where the impact toughness reaches 103.6 J/cm^(2),representing an impressive improvement of 87.3%.
基金the State’s Key Project of Research and Development Plan under Grant 2022YFB2701400in part by the National Natural Science Foundation of China under Grants 62272124 and 62361010+4 种基金in part by the Science and Technology Planning Project of Guizhou Province under Grant[2020]5017in part by the Research Project of Guizhou University for Talent Introduction underGrant[2020]61in part by theCultivation Project of Guizhou University under Grant[2019]56in part by the Open Fund of Key Laboratory of Advanced Manufacturing Technology,Ministry of Education under Grant GZUAMT2021KF[01]the Science and Technology Program of Guizhou Province(No.[2023]371).
文摘Traditional blockchain key management schemes store private keys in the same location,which can easily lead to security issues such as a single point of failure.Therefore,decentralized threshold key management schemes have become a research focus for blockchain private key protection.The security of private keys for blockchain user wallet is highly related to user identity authentication and digital asset security.The threshold blockchain private key management schemes based on verifiable secret sharing have made some progress,but these schemes do not consider participants’self-interested behavior,and require trusted nodes to keep private key fragments,resulting in a narrow application scope and low deployment efficiency,which cannot meet the needs of personal wallet private key escrow and recovery in public blockchains.We design a private key management scheme based on rational secret sharing that considers the self-interest of participants in secret sharing protocols,and constrains the behavior of rational participants through reasonable mechanism design,making it more suitable in distributed scenarios such as the public blockchain.The proposed scheme achieves the escrow and recovery of personal wallet private keys without the participation of trusted nodes,and simulate its implementation on smart contracts.Compared to other existing threshold wallet solutions and keymanagement schemes based on password-protected secret sharing(PPSS),the proposed scheme has a wide range of applications,verifiable private key recovery,low communication overhead,higher computational efficiency when users perform one-time multi-key escrow,no need for trusted nodes,and personal rational constraints and anti-collusion attack capabilities.
