Resisting Poisoning Attacks in Federated Learning via Dual-Domain Distance and Trust Assessment

Subsequently, by executing various attacks on benchmark datasets such as MNIST, we construct Federated Learning Malicious Parameter Identification (FLMPID) dataset to enable malicious client detection. Building on this dataset, we propose FORTRESS (Federated POisoning-Resistance Defense via Dual-Domain Distance and TRust AssESSment), a framework designed to detect and mitigate malicious updates from clients. FORTRESS employs a unique encoder-decoder architecture. The encoder utilizes dual-domain distance metrics on weights and gradients to extract hidden representations, while the decoder leverages Actor-Critic (AC) reinforcement learning for trust assessment. We evaluated FORTRESS under multiple attack scenarios and demonstrated its defense effectiveness, making it a promising solution for enhancing the security of FL systems.

Authors

Institutions

Publication Details

Journal
IEEE Transactions on Information Forensics and Security
Published
2025-01-01
DOI
https://doi.org/10.1109/tifs.2025.3589061
Citations
3
Primary Topic
Privacy-Preserving Technologies in Data
Type
article
Field-Weighted Citation Impact
7.44

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Resisting Poisoning Attacks in Federated Learning via Dual-Domain Distance and Trust Assessment

Yan Wu, Wei Liang, Zijian Zhang, Zhen Li et al.
3 citations
IEEE Transactions on Information Forensics and Security
Privacy-Preserving Technologies in Data
7.44
article

Resisting Poisoning Attacks in Federated Learning via Dual-Domain Distance and Trust Assessment

Yan Wu, Wei Liang, Zijian Zhang, Zhen Li, Ye Liu, Xin Li, Yong Liu, Meng Li, Zhaoqi Wang, Liehuang Zhu, Jincheng An
article en
3 citations

Abstract

Subsequently, by executing various attacks on benchmark datasets such as MNIST, we construct Federated Learning Malicious Parameter Identification (FLMPID) dataset to enable malicious client detection. Building on this dataset, we propose FORTRESS (Federated POisoning-Resistance Defense via Dual-Domain Distance and TRust AssESSment), a framework designed to detect and mitigate malicious updates from clients. FORTRESS employs a unique encoder-decoder architecture. The encoder utilizes dual-domain distance metrics on weights and gradients to extract hidden representations, while the decoder leverages Actor-Critic (AC) reinforcement learning for trust assessment. We evaluated FORTRESS under multiple attack scenarios and demonstrated its defense effectiveness, making it a promising solution for enhancing the security of FL systems.

IEEE Transactions on Information Forensics and SecurityVol. 20
Hunan University of Science and Technology (CN), Beijing Institute of Technology (CN), Anhui University (CN), Hefei University of Technology (CN), Sino Biological (China) (CN), China XD Group (China) (CN), China Information Technology Security Evaluation Center (CN), Singapore Management University (SG)
National Natural Science Foundation of China, China Scholarship Council
Openalex Percentile: Top 3%
Privacy-Preserving Technologies in Data
7.44
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.