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

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

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
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.

Distributed machine learning securityFederated learningData poisoning attacksData sanitizationBatch detectionData complexity

Silv Wang、Kai Fan、Kuan Zhang、Hui Li、Yintang Yang

展开 >

State Key Laboratory of Integrated Service Networks,Xidian University,Xi'an,710126,China

Department of Electrical and Computer Engineering,University of Nebraska-Lincoln,Lincoln,NE,68588,USA

Key Lab.of the Minist. of Educ.for Wide Bandgap Semiconductor Materials and Devices,Xidian University,Xi'an 710071,China

the"Pioneer"and"Leading Goose"R&D Program of ZhejiangNational Natural Science Foundation of ChinaKey Research and Development Program of Shaanxi,ChinaNatural Science Foundation of Shaanxi ProvinceShaanxi Innovation Team ProjectXi'an science and technology Innovation PlanFundamental Research Funds for the Central UniversitiesNational 111 Program of China

2022C03174920671032021ZDLGY06-022019ZDLGY12-022018TD-007201809168CX9JC10YJS2212B16037

2024

10.1016/j.dcan.2022.12.001

数字通信与网络(英文)

数字通信与网络(英文)

ISSN：
年,卷(期)：2024.10(2)
  • 40