Byzantine Robust

Byzantine robustness in distributed machine learning focuses on developing algorithms and systems resilient to malicious or faulty nodes ("Byzantine workers") that can disrupt the training process by sending corrupted data or model updates. Current research emphasizes developing efficient and communication-friendly aggregation methods, often incorporating techniques like trimmed mean, median, or more sophisticated approaches such as quadratic voting or dynamic defense strategies, to filter out or mitigate the impact of Byzantine nodes in various architectures, including centralized, decentralized, and federated learning settings. This field is crucial for ensuring the reliability and security of large-scale machine learning systems, particularly in applications where data privacy and model integrity are paramount.

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 13, 2024

Byzantine-Robust and Communication-Efficient Distributed Learning via Compressed Momentum Filtering
Changxin Liu, Yanghao Li, Yuhao Yi, Karl H. Johansson
LeArning Abstract Communication Efficient Byzantine Robust Momentum Based Byzantine Failure

August 12, 2024

Understanding Byzantine Robustness in Federated Learning with A Black-box Server
Fangyuan Zhao, Yuexiang Xie, Xuebin Ren, Bolin Ding, Shusen Yang, Yaliang Li
Black Box Byzantine Robust Byzantine Attack

July 19, 2024

Byzantine-tolerant distributed learning of finite mixture models
Qiong Zhang, Jiahua Chen
LeArning Abstract Split Learning Byzantine Robust Finite Mixture Byzantine Failure

July 6, 2024

Impact of Network Topology on Byzantine Resilience in Decentralized Federated Learning
Siddhartha Bhattacharya, Daniel Helo, Joshua Siegel
Global Impact Decentralized Federated Learning Network Topology Byzantine Robust Byzantine Robust Aggregation Byzantine Resilience

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

No Vandalism: Privacy-Preserving and Byzantine-Robust Federated Learning
Zhibo Xing, Zijian Zhang, Zi'ang Zhang, Jiamou Liu, Liehuang Zhu, Giovanni Russello
Secure Aggregation Byzantine Robust Zero Knowledge Model Poisoning Attack Byzantine Robust Federated Learning Vandalism Detection

May 23, 2024

Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training
Tehila Dahan, Kfir Y. Levy
Machine Learning Stochastic Convex Optimization Byzantine Robust Asynchronous Training Aware Aggregator

May 1, 2024

On the Relevance of Byzantine Robust Optimization Against Data Poisoning
Sadegh Farhadkhani, Rachid Guerraoui, Nirupam Gupta, Rafael Pinot
Relative Relevance Data Poisoning Byzantine Robust Poisoned Data Byzantine Machine Learning

February 16, 2024

TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Data
Richeng Jin, Yujie Gu, Kai Yue, Xiaofan He, Zhaoyang Zhang, Huaiyu Dai
Differential Privacy Heterogeneous Data Communication Efficiency Byzantine Robust Privacy Amplification Ternary Random Variable

February 5, 2024

Dynamic Byzantine-Robust Learning: Adapting to Switching Byzantine Workers
Ron Dorfman, Naseem Yehya, Kfir Y. Levy
Learning Rate Byzantine Robust Byzantine Seal Byzantine Failure Time Varying Impedance Attack

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

January 2, 2024

FedQV: Leveraging Quadratic Voting in Federated Learning
Tianyue Chu, Nikolaos Laoutaris
Byzantine Robust Voting Method

November 26, 2023

Secure and Verifiable Data Collaboration with Low-Cost Zero-Knowledge Proofs
Yizheng Zhu, Yuncheng Wu, Zhaojing Luo, Beng Chin Ooi, Xiaokui Xiao
Secure Aggregation Byzantine Robust Secure Approach Zero Knowledge Data Collaboration

November 23, 2023

Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
Grigory Malinovsky, Peter Richtárik, Samuel Horváth, Eduard Gorbunov
Machine Learning Model Variance Reduction Byzantine Robust Client Sampling Gradient Clipping Byzantine Fault Tolerance Partial Participation Byzantine Robust Method

November 17, 2023

FedTruth: Byzantine-Robust and Backdoor-Resilient Federated Learning Framework
Sheldon C. Ebron, Kan Yang
Federated Learning Byzantine Robust Robust Defense Model Poisoning Attack Malicious Client

November 13, 2023

AGRAMPLIFIER: Defending Federated Learning Against Poisoning Attacks Through Local Update Amplification
Zirui Gong, Liyue Shen, Yanjun Zhang, Leo Yu Zhang, Jingwei Wang, Guangdong Bai, Yong Xiang
Poisoning Attack Byzantine Robust Byzantine Attack Byzantine Robust Aggregation Local Update

November 8, 2023

Byzantine-Tolerant Methods for Distributed Variational Inequalities
Nazarii Tupitsa, Abdulla Jasem Almansoori, Yanlin Wu, Martin Takáč, Karthik Nandakumar, Samuel Horváth, Eduard Gorbunov
Byzantine Robust Variational Inequality Byzantine Attack 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

October 15, 2023

Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates
Ahmad Rammal, Kaja Gruntkowska, Nikita Fedin, Eduard Gorbunov, Peter Richtárik
Novel Algorithm Byzantine Robust Fast Rate Communication Compression Smooth Convex Optimization Byzantine Robust Method