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

Silv Wang ¹Kai Fan ¹Kuan Zhang ²Hui Li ¹Yintang Yang³

扫码查看

作者信息

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
折叠

Abstract

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.

Key words

Distributed machine learning security/Federated learning/Data poisoning attacks/Data sanitization/Batch detection/Data complexity

引用本文复制引用

基金项目

the"Pioneer"and"Leading Goose"R&D Program of Zhejiang(2022C03174)

National Natural Science Foundation of China(92067103)

Key Research and Development Program of Shaanxi,China(2021ZDLGY06-02)

Natural Science Foundation of Shaanxi Province(2019ZDLGY12-02)

Shaanxi Innovation Team Project(2018TD-007)

Xi'an science and technology Innovation Plan(201809168CX9JC10)

Fundamental Research Funds for the Central Universities(YJS2212)

National 111 Program of China(B16037)

出版年

2024

数字通信与网络(英文)

ISSN：

参考文献量40

段落导航