EMNLP Findings2024
Enhancing Byzantine-Resistant Aggregations with Client Embedding
Zhiyuan Zhang, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun
Abstract
Byzantine-resistant aggregations detect poisonous clients and discard them to ensure that the global model is not poisoned or attacked by malicious clients. However, these aggregations are mainly conducted on the parameter space, and the parameter distances cannot reflect the data distribution divergences between clients. Therefore, existing Byzantine-resistant aggregations cannot defend against backdoor injection by malicious attackers in federated natural language tasks. In this paper, we propose the client embedding for malicious client detection to enhance Byzantine-resistant aggregations. The distances between client embeddings are required to reflect the data distribution divergences of the corresponding clients. Experimental results validate the effectiveness of the proposed client embeddings.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation cites Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms
- Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation cites CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
- Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense cites Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation
- Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense cites Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms
- Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense cites CRFL: Certifiably Robust Federated Learning against Backdoor Attacks
Builds on4
- CRFL: Certifiably Robust Federated Learning against Backdoor AttacksChulin Xie, Minghao Chen, Pin-Yu Chen, Bo LiICML 2021 · 218 citations
- Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based AlgorithmsXiangyi Chen, Tiancong Chen, Haoran Sun, Zhiwei Steven Wu et al.NeurIPS 2020 · 90 citations
- Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based AggregationZhiyuan Zhang, Qi Su, Xu SunEMNLP Findings 2022 · 16 citations
- Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor DefenseZhiyuan Zhang, Deli Chen, Hao Zhou, Fandong Meng et al.NeurIPS 2023 · 10 citations
Related papers
- Backdoor Attacks in Federated Learning by Rare Embeddings and Gradient EnsemblingKiYoon Yoo, Nojun KwakEMNLP 2022 · 24 citations
- DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model InspectionPhillip Rieger, Thien Duc Nguyen, Markus Miettinen, Ahmad-Reza SadeghiNDSS 2022
- Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated LearningYujing Wang, Hainan Zhang, Sijia Wen, Wangjie Qiu et al.AAAI 2025 · 4 citations
- BayBFed: Bayesian Backdoor Defense for Federated LearningKavita Kumari, Phillip Rieger, Hossein Fereidooni, Murtuza Jadliwala et al.S&P 2023
- DeFL: Defending against Model Poisoning Attacks in Federated Learning via Critical Learning Periods AwarenessGang Yan, Hao Wang, Xu Yuan, Jian LiAAAI 2023 · 38 citations
