摘要
针对边端协同联邦学习中边缘服务器与设备终端频繁交互更新模型和梯度参数时,窃听者容易通过导频攻击干扰信道估计,从而达到降低模型更新效率和窃取模型参数的问题,基于异构导频能量估计提出一种导频攻击检测算法。首先,通过深入分析导频攻击对系统安全速率的影响,构建联邦学习导频攻击系统模型。进而,基于随机分割和加密方法提出一种信号平均能量差的导频攻击检测方法,能够准确地检测出潜在的导频攻击并进行污染信道的恢复。实验结果表明,与其他已有算法相比,所提算法适用于检测发射功率小、隐蔽性强的导频攻击,基于恢复的信道状态信息进行预编码可以大幅度提高边缘服务器的数据传输速率。
For the federated learning scenarios with edge-end cooperation,edge servers and device terminals update their models and exchange gradient parameters frequently,and hence eavesdroppers can manipulate channel estimation through pilot spoofing to intercept the transmitted information and reduce the update efficiency of federated learning model.Therefore,a pilot attack detection algorithm with heterogeneous pilot energy estimation was proposed.Firstly,a federated learning pilot attack system model was constructed after the security of pilot attacks on data transmission had been analyzed.Then,a pilot attack detection method based on random segmentation and encryption methods was proposed to detect the pilot spoofing accurately and the contaminated channel could be recovered as well.Experimental results show that the proposed algorithm is more suitable for detecting pilot attacks with low transmit power and strong concealment compared to other existing algorithms.Furthermore,the data transmission rate of edge servers is improved significantly through the precoding based on the recovered channel state information.
作者
王仕果
田淑娟
邓清勇
WANG Shiguo;TIAN Shujuan;DENG Qingyong(School of Computer and Communication Engineering,Changsha University of Science and Technology,Changsha 410076,China;College of Computer,Xiangtan University,Xiangtan 411105,China;School of Computer,Guangxi Normal University,Guilin 541001,China)
出处
《通信学报》
EI
CSCD
北大核心
2023年第11期120-128,共9页
Journal on Communications
基金
国家自然科学基金资助项目(No.62372065,No.62172349,No.62076214)
湖南省自然科学基金项目(No.2023JJ30597,No.2021JJ30737)
湖南省教育厅基金资助项目(No.21B0139)
中国科学院计算科学国家重点实验室开放基金资助项目(No.SYSKF2101)。
关键词
导频攻击检测
能量估计
攻击对抗
边缘计算
pilot spoofing detection
energy estimation
attack combating
edge computing
