Byzantine Robust Federated Learning

Byzantine-robust federated learning (FL) aims to secure collaborative model training across multiple clients against malicious actors (Byzantine clients) who inject faulty updates. Current research focuses on developing robust aggregation algorithms, often employing techniques like geometric medians, normalized gradients, or layer-adaptive sparsification, to filter out malicious updates and ensure convergence even with a significant fraction of compromised clients. These advancements are crucial for deploying secure and reliable FL systems in various applications, addressing vulnerabilities to data poisoning and model manipulation attacks while maintaining efficiency and privacy. The field is actively exploring both centralized and decentralized architectures, incorporating techniques like clustering and asynchronous updates to improve robustness and scalability.

Papers

October 30, 2024

Byzantine-Robust Federated Learning: An Overview With Focus on Developing Sybil-based Attacks to Backdoor Augmented Secure Aggregation Protocols
Atharv Deshmukh
Native Robustness Secure Aggregation Byzantine Robust Byzantine Attack Population Protocol Byzantine Robust Federated Learning

September 2, 2024

Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregation
Jiahao Xu, Zikai Zhang, Rui Hu
Random Sparsification Robust Aggregation Byzantine Robust Federated Learning Model Sparsification

August 18, 2024

Byzantine-resilient Federated Learning Employing Normalized Gradients on Non-IID Datasets
Shiyuan Zuo, Xingrun Yan, Rongfei Fan, Li Shen, Puning Zhao, Jie Xu, Han Hu
Data Set Non Convex Loss Function Byzantine Robust Federated Learning Federated Learning Approach Optimality Gap Federated Stochastic Byzantine Robust Method

June 20, 2024

Communication-Efficient Byzantine-Resilient Federated Zero-Order Optimization
Afonso de Sá Delgado Neto, Maximilian Egger, Mayank Bakshi, Rawad Bitar
Federated Learning Byzantine Robust Federated Learning Zeroth Order Optimization Byzantine Fault Memory and Communication

June 18, 2024

BadSampler: Harnessing the Power of Catastrophic Forgetting to Poison Byzantine-robust Federated Learning
Yi Liu, Cong Wang, Xingliang Yuan
Catastrophic Forgetting Real Power Byzantine Robust Federated Learning Byzantine Robust Aggregation Label Poisoning Attack

June 14, 2024

Byzantine-Robust Decentralized Federated Learning
Minghong Fang, Zifan Zhang, Hairi, Prashant Khanduri, Jia Liu, Songtao Lu, Yuchen Liu, Neil Gong
Decentralized FL Byzantine Robust Byzantine Robust Federated Learning

June 3, 2024

March 20, 2024

Byzantine-resilient Federated Learning With Adaptivity to Data Heterogeneity
Shiyuan Zuo, Xingrun Yan, Rongfei Fan, Han Hu, Hangguan Shan, Tony Q. S. Quek
Adaptive Importance Data Heterogeneity Non Convex Loss Function Byzantine Attack Byzantine Robust Federated Learning Convex Loss Function

March 5, 2024

FLGuard: Byzantine-Robust Federated Learning via Ensemble of Contrastive Models
Younghan Lee, Yungi Cho, Woorim Han, Ho Bae, Yunheung Paek
Diverse Ensemble State of the Art Defense Private Training Byzantine Robust Federated Learning Contrastive Model

February 20, 2024

Byzantine-Robust Federated Learning: Impact of Client Subsampling and Local Updates
Youssef Allouah, Sadegh Farhadkhani, Rachid GuerraouI, Nirupam Gupta, Rafael Pinot, Geovani Rizk, Sasha Voitovych
Global Impact Adversarial Behavior Local Context Byzantine Robust Federated Learning Client Sampling

January 7, 2024

Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence
Philip Jordan, Florian Grötschla, Flint Xiaofeng Fan, Roger Wattenhofer
Federated Reinforcement Learning Byzantine Robust Byzantine Robust Federated Learning Exponential Convergence Rate Byzantine Fault Tolerance Federated Offline Reinforcement Learning

December 19, 2023

SkyMask: Attack-agnostic Robust Federated Learning with Fine-grained Learnable Masks
Peishen Yan, Hao Wang, Tao Song, Yang Hua, Ruhui Ma, Ningxin Hu, Mohammad R. Haghighat, Haibing Guan
Fine Grained Byzantine Robust Federated Learning Robust Federated Learning Malicious Model

December 2, 2023

PROFL: A Privacy-Preserving Federated Learning Method with Stringent Defense Against Poisoning Attacks
Yisheng Zhong, Li-Ping Wang
Federated Learning Poisoning Attack Homomorphic Encryption Byzantine Robust Federated Learning Byzantine Robust Method

October 20, 2023

BRFL: A Blockchain-based Byzantine-Robust Federated Learning Model
Yang Li, Chunhe Xia, Chang Li, Tianbo Wang
Byzantine Robust Byzantine Robust Federated Learning Byzantine Robust Aggregation Byzantine Fault

September 7, 2023

Byzantine-Robust Federated Learning with Variance Reduction and Differential Privacy
Zikai Zhang, Rui Hu
Differential Privacy Privacy Guarantee Variance Reduction Privacy Analysis Byzantine Attack Byzantine Robust Federated Learning Client Level Differential Privacy

August 24, 2023

A Huber Loss Minimization Approach to Byzantine Robust Federated Learning
Puning Zhao, Fei Yu, Zhiguo Wan
Adversarial Attack Federated Learning Byzantine Robust Federated Learning Huber Loss Optimal Dependence Modern News Aggregator

June 1, 2023

Byzantine-Robust Clustered Federated Learning
Zhixu Tao, Kun Yang, Sanjeev R. Kulkarni
Adversarial Attack Byzantine Robust Federated Learning Byzantine Failure

April 15, 2023

Practical Differentially Private and Byzantine-resilient Federated Learning
Zihang Xiang, Tianhao Wang, Wanyu Lin, Di Wang
Practical Application Private Stochastic Byzantine Robust Federated Learning Byzantine Robust Aggregation Byzantine Resilience Byzantine Failure

March 18, 2023

Byzantine-Resilient Federated Learning at Edge
Youming Tao, Sijia Cui, Wenlu Xu, Haofei Yin, Dongxiao Yu, Weifa Liang, Xiuzhen Cheng
Extreme Edge Heavy Tailed Stochastic Convex Optimization Byzantine Robust Federated Learning Byzantine Resilience Byzantine Fault