Data complexity-based batch sanitization method against poison in distributed learning  

作　　者：Silv Wang Kai Fan Kuan Zhang Hui Li Yintang Yang 

机构地区：[1]State Key Laboratory of Integrated Service Networks,Xidian University,Xi'an,710126,China [2]Department of Electrical and Computer Engineering,University of Nebraska-Lincoln,Lincoln,NE,68588,USA [3]Key Lab.of the Minist.of Educ.for Wide Bandgap Semiconductor Materials and Devices,Xidian University,Xi'an,710071,China

出　　处：《Digital Communications and Networks》2024年第2期416-428,共13页数字通信与网络（英文版）

基　　金：supported in part by the“Pioneer”and“Leading Goose”R&D Program of Zhejiang(Grant No.2022C03174);the National Natural Science Foundation of China(No.92067103);the Key Research and Development Program of Shaanxi,China(No.2021ZDLGY06-02);the Natural Science Foundation of Shaanxi Province(No.2019ZDLGY12-02);the Shaanxi Innovation Team Project(No.2018TD-007);the Xi'an Science and technology Innovation Plan(No.201809168CX9JC10);the Fundamental Research Funds for the Central Universities(No.YJS2212)and National 111 Program of China B16037.

摘　　要：The security of Federated Learning(FL)/Distributed Machine Learning(DML)is gravely threatened by data poisoning attacks,which destroy the usability of the model by contaminating training samples,so such attacks are called causative availability indiscriminate attacks.Facing the problem that existing data sanitization methods are hard to apply to real-time applications due to their tedious process and heavy computations,we propose a new supervised batch detection method for poison,which can fleetly sanitize the training dataset before the local model training.We design a training dataset generation method that helps to enhance accuracy and uses data complexity features to train a detection model,which will be used in an efficient batch hierarchical detection process.Our model stockpiles knowledge about poison,which can be expanded by retraining to adapt to new attacks.Being neither attack-specific nor scenario-specific,our method is applicable to FL/DML or other online or offline scenarios.

关 键 词：Distributed machine learning security Federated learning Data poisoning attacks Data sanitization Batch detection Data complexity 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]