This study investigates resilient platoon control for constrained intelligent and connected vehicles(ICVs)against F-local Byzantine attacks.We introduce a resilient distributed model-predictive platooning control fram...This study investigates resilient platoon control for constrained intelligent and connected vehicles(ICVs)against F-local Byzantine attacks.We introduce a resilient distributed model-predictive platooning control framework for such ICVs.This framework seamlessly integrates the predesigned optimal control with distributed model predictive control(DMPC)optimization and introduces a unique distributed attack detector to ensure the reliability of the transmitted information among vehicles.Notably,our strategy uses previously broadcasted information and a specialized convex set,termed the“resilience set”,to identify unreliable data.This approach significantly eases graph robustness prerequisites,requiring only an(F+1)-robust graph,in contrast to the established mean sequence reduced algorithms,which require a minimum(2F+1)-robust graph.Additionally,we introduce a verification algorithm to restore trust in vehicles under minor attacks,further reducing communication network robustness.Our analysis demonstrates the recursive feasibility of the DMPC optimization.Furthermore,the proposed method achieves exceptional control performance by minimizing the discrepancies between the DMPC control inputs and predesigned platoon control inputs,while ensuring constraint compliance and cybersecurity.Simulation results verify the effectiveness of our theoretical findings.展开更多
In vehicle edge computing(VEC),asynchronous federated learning(AFL)is used,where the edge receives a local model and updates the global model,effectively reducing the global aggregation latency.Due to different amount...In vehicle edge computing(VEC),asynchronous federated learning(AFL)is used,where the edge receives a local model and updates the global model,effectively reducing the global aggregation latency.Due to different amounts of local data,computing capabilities and locations of the vehicles,renewing the global model with same weight is inappropriate.The above factors will affect the local calculation time and upload time of the local model,and the vehicle may also be affected by Byzantine attacks,leading to the deterioration of the vehicle data.However,based on deep reinforcement learning(DRL),we can consider these factors comprehensively to eliminate vehicles with poor performance as much as possible and exclude vehicles that have suffered Byzantine attacks before AFL.At the same time,when aggregating AFL,we can focus on those vehicles with better performance to improve the accuracy and safety of the system.In this paper,we proposed a vehicle selection scheme based on DRL in VEC.In this scheme,vehicle’s mobility,channel conditions with temporal variations,computational resources with temporal variations,different data amount,transmission channel status of vehicles as well as Byzantine attacks were taken into account.Simulation results show that the proposed scheme effectively improves the safety and accuracy of the global model.展开更多
Federated learning is widely used to solve the problem of data decentralization and can provide privacy protectionfor data owners. However, since multiple participants are required in federated learning, this allows a...Federated learning is widely used to solve the problem of data decentralization and can provide privacy protectionfor data owners. However, since multiple participants are required in federated learning, this allows attackers tocompromise. Byzantine attacks pose great threats to federated learning. Byzantine attackers upload maliciouslycreated local models to the server to affect the prediction performance and training speed of the global model. Todefend against Byzantine attacks, we propose a Byzantine robust federated learning scheme based on backdoortriggers. In our scheme, backdoor triggers are embedded into benign data samples, and then malicious localmodels can be identified by the server according to its validation dataset. Furthermore, we calculate the adjustmentfactors of local models according to the parameters of their final layers, which are used to defend against datapoisoning-based Byzantine attacks. To further enhance the robustness of our scheme, each localmodel is weightedand aggregated according to the number of times it is identified as malicious. Relevant experimental data showthat our scheme is effective against Byzantine attacks in both independent identically distributed (IID) and nonindependentidentically distributed (non-IID) scenarios.展开更多
To deal with Byzantine attacks in 5 G cognitive radio networks,a bilateral threshold selection-based algorithm is proposed in the spectrum sensing process. In each round,secondary uses( SUs) first submit the energy va...To deal with Byzantine attacks in 5 G cognitive radio networks,a bilateral threshold selection-based algorithm is proposed in the spectrum sensing process. In each round,secondary uses( SUs) first submit the energy values and instantaneous detection signal-to-noise ratios( SNRs) to the fusion center( FC). According to detection SNRs,the FC conducts normalization calculations on the energy values. Then,the FC makes a sort operation for these normalized energy values and traverses all the possible mid-points between these sorted normalized energy values to maximize the classification accuracy of each SU. Finally,by introducing the recognition probability and misclassification probability,the distributions of the normalized energy values are analyzed and the bilateral threshold of classification accuracy is obtained via a target misclassification probability. Hence,the blacklist of malicious secondary users( MSUs) is obtained. Simulation results show that the proposed scheme outperforms the current mainstream schemes in correct sensing probability,false alarm probability and detection probability.展开更多
In order to solve the Byzantine attack problem in cooperative spectrum sensing,a non-cooperative game-theory approach is proposed to realize an effective Byzantine defense.First,under the framework of the proposed non...In order to solve the Byzantine attack problem in cooperative spectrum sensing,a non-cooperative game-theory approach is proposed to realize an effective Byzantine defense.First,under the framework of the proposed non-cooperative game theory,the pure Byzantine attack strategy and defense strategy in cooperative spectrum sensing are analyzed from the perspective of the Byzantine attacker and network administrator.The cost and benefit of the pure strategy on both sides are defined. Secondly,the mixed attack and defense strategy are also derived. The closed form Nash equilibrium is obtained by the Lemke-Howson algorithm. Furthermore,the impact of the benefit ratio and penalty rate on the dynamic process of the noncooperative game is analyzed. Numerical simulation results show that the proposed game-theory approach can effectively defend against the Byzantine attack and save the defensive cost.展开更多
The secure and normal operation of distributed networks is crucial for accurate parameter estimation.However,distributed networks are frequently susceptible to Byzantine attacks.Considering real-life scenarios,this pa...The secure and normal operation of distributed networks is crucial for accurate parameter estimation.However,distributed networks are frequently susceptible to Byzantine attacks.Considering real-life scenarios,this paper investigates a probability Byzantine(PB)attack,utilizing a Bernoulli distribution to simulate the attack probability.Historically,additional detection mechanisms are used to mitigate such attacks,leading to increased energy consumption and burdens on distributed nodes,consequently diminishing operational efficiency.Differing from these approaches,an adaptive updating distributed estimation algorithm is proposed to mitigate the impact of PB attacks.In the proposed algorithm,a penalty strategy is initially incorporated during data updates to weaken the influence of the attack.Subsequently,an adaptive fusion weight is employed during data fusion to merge the estimations.Additionally,the reason why this penalty term weakens the attack has been analyzed,and the performance of the proposed algorithm is validated through simulation experiments.展开更多
基金the financial support from the Natural Sciences and Engineering Research Council of Canada(NSERC)。
文摘This study investigates resilient platoon control for constrained intelligent and connected vehicles(ICVs)against F-local Byzantine attacks.We introduce a resilient distributed model-predictive platooning control framework for such ICVs.This framework seamlessly integrates the predesigned optimal control with distributed model predictive control(DMPC)optimization and introduces a unique distributed attack detector to ensure the reliability of the transmitted information among vehicles.Notably,our strategy uses previously broadcasted information and a specialized convex set,termed the“resilience set”,to identify unreliable data.This approach significantly eases graph robustness prerequisites,requiring only an(F+1)-robust graph,in contrast to the established mean sequence reduced algorithms,which require a minimum(2F+1)-robust graph.Additionally,we introduce a verification algorithm to restore trust in vehicles under minor attacks,further reducing communication network robustness.Our analysis demonstrates the recursive feasibility of the DMPC optimization.Furthermore,the proposed method achieves exceptional control performance by minimizing the discrepancies between the DMPC control inputs and predesigned platoon control inputs,while ensuring constraint compliance and cybersecurity.Simulation results verify the effectiveness of our theoretical findings.
基金supported in part by the National Natural Science Foundation of China(No.61701197)in part by the National Key Research and Development Program of China(No.2021YFA1000500(4))in part by the 111 Project(No.B23008).
文摘In vehicle edge computing(VEC),asynchronous federated learning(AFL)is used,where the edge receives a local model and updates the global model,effectively reducing the global aggregation latency.Due to different amounts of local data,computing capabilities and locations of the vehicles,renewing the global model with same weight is inappropriate.The above factors will affect the local calculation time and upload time of the local model,and the vehicle may also be affected by Byzantine attacks,leading to the deterioration of the vehicle data.However,based on deep reinforcement learning(DRL),we can consider these factors comprehensively to eliminate vehicles with poor performance as much as possible and exclude vehicles that have suffered Byzantine attacks before AFL.At the same time,when aggregating AFL,we can focus on those vehicles with better performance to improve the accuracy and safety of the system.In this paper,we proposed a vehicle selection scheme based on DRL in VEC.In this scheme,vehicle’s mobility,channel conditions with temporal variations,computational resources with temporal variations,different data amount,transmission channel status of vehicles as well as Byzantine attacks were taken into account.Simulation results show that the proposed scheme effectively improves the safety and accuracy of the global model.
基金in part by the National Social Science Foundation of China under Grant 20BTQ058in part by the Natural Science Foundation of Hunan Province under Grant 2023JJ50033。
文摘Federated learning is widely used to solve the problem of data decentralization and can provide privacy protectionfor data owners. However, since multiple participants are required in federated learning, this allows attackers tocompromise. Byzantine attacks pose great threats to federated learning. Byzantine attackers upload maliciouslycreated local models to the server to affect the prediction performance and training speed of the global model. Todefend against Byzantine attacks, we propose a Byzantine robust federated learning scheme based on backdoortriggers. In our scheme, backdoor triggers are embedded into benign data samples, and then malicious localmodels can be identified by the server according to its validation dataset. Furthermore, we calculate the adjustmentfactors of local models according to the parameters of their final layers, which are used to defend against datapoisoning-based Byzantine attacks. To further enhance the robustness of our scheme, each localmodel is weightedand aggregated according to the number of times it is identified as malicious. Relevant experimental data showthat our scheme is effective against Byzantine attacks in both independent identically distributed (IID) and nonindependentidentically distributed (non-IID) scenarios.
基金The National Natural Science Foundation of China(No.61771126,61372104)the Science and Technology Project of State Grid Corporation of China(No.SGRIXTKJ[2015]349)
文摘To deal with Byzantine attacks in 5 G cognitive radio networks,a bilateral threshold selection-based algorithm is proposed in the spectrum sensing process. In each round,secondary uses( SUs) first submit the energy values and instantaneous detection signal-to-noise ratios( SNRs) to the fusion center( FC). According to detection SNRs,the FC conducts normalization calculations on the energy values. Then,the FC makes a sort operation for these normalized energy values and traverses all the possible mid-points between these sorted normalized energy values to maximize the classification accuracy of each SU. Finally,by introducing the recognition probability and misclassification probability,the distributions of the normalized energy values are analyzed and the bilateral threshold of classification accuracy is obtained via a target misclassification probability. Hence,the blacklist of malicious secondary users( MSUs) is obtained. Simulation results show that the proposed scheme outperforms the current mainstream schemes in correct sensing probability,false alarm probability and detection probability.
基金The National Natural Science Foundation of China(No.61771126)
文摘In order to solve the Byzantine attack problem in cooperative spectrum sensing,a non-cooperative game-theory approach is proposed to realize an effective Byzantine defense.First,under the framework of the proposed non-cooperative game theory,the pure Byzantine attack strategy and defense strategy in cooperative spectrum sensing are analyzed from the perspective of the Byzantine attacker and network administrator.The cost and benefit of the pure strategy on both sides are defined. Secondly,the mixed attack and defense strategy are also derived. The closed form Nash equilibrium is obtained by the Lemke-Howson algorithm. Furthermore,the impact of the benefit ratio and penalty rate on the dynamic process of the noncooperative game is analyzed. Numerical simulation results show that the proposed game-theory approach can effectively defend against the Byzantine attack and save the defensive cost.
文摘The secure and normal operation of distributed networks is crucial for accurate parameter estimation.However,distributed networks are frequently susceptible to Byzantine attacks.Considering real-life scenarios,this paper investigates a probability Byzantine(PB)attack,utilizing a Bernoulli distribution to simulate the attack probability.Historically,additional detection mechanisms are used to mitigate such attacks,leading to increased energy consumption and burdens on distributed nodes,consequently diminishing operational efficiency.Differing from these approaches,an adaptive updating distributed estimation algorithm is proposed to mitigate the impact of PB attacks.In the proposed algorithm,a penalty strategy is initially incorporated during data updates to weaken the influence of the attack.Subsequently,an adaptive fusion weight is employed during data fusion to merge the estimations.Additionally,the reason why this penalty term weakens the attack has been analyzed,and the performance of the proposed algorithm is validated through simulation experiments.
