Byzantine Robust Aggregation

Byzantine robust aggregation focuses on securing distributed machine learning, particularly federated learning, against malicious nodes (Byzantine nodes) that inject faulty data or model updates. Current research emphasizes developing aggregation algorithms that are resilient to various attacks, including data poisoning and gradient inversion, across diverse network topologies, and often incorporates techniques like median calculations, clustering, and coded computing to identify and mitigate these attacks. This field is crucial for ensuring the reliability and trustworthiness of decentralized machine learning systems, impacting the security and privacy of applications ranging from medical diagnosis to autonomous vehicles.

Papers

October 9, 2024

PFAttack: Stealthy Attack Bypassing Group Fairness in Federated Learning
Jiashi Gao, Ziwei Wang, Xiangyu Zhao, Xin Yao, Xuetao Wei
Group Fairness Byzantine Robust Aggregation Fairness Attack

September 26, 2024

Byzantine-Robust Aggregation for Securing Decentralized Federated Learning
Diego Cajaraville-Aboy, Ana Fernández-Vilas, Rebeca P. Díaz-Redondo, Manuel Fernández-Veiga
Decentralized Federated Learning Byzantine Robust Aggregation Byzantine Robust Method

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 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

May 14, 2024

Byzantine-Resilient Secure Aggregation for Federated Learning Without Privacy Compromises
Yue Xia, Christoph Hofmeister, Maximilian Egger, Rawad Bitar
Calysto Scheme Secret Sharing Privacy Preserving Computation Byzantine Robust Aggregation Byzantine Robust Method

March 5, 2024

Robust Federated Learning Mitigates Client-side Training Data Distribution Inference Attacks
Yichang Xu, Ming Yin, Minghong Fang, Neil Zhenqiang Gong
Adaptive Attack Byzantine Robust Aggregation

February 6, 2024

Towards Fair, Robust and Efficient Client Contribution Evaluation in Federated Learning
Meiying Zhang, Huan Zhao, Sheldon Ebron, Kan Yang
Robust Version Client Contribution Byzantine Attack Byzantine Robust Aggregation Client Centered Assessment

December 22, 2023

Attacking Byzantine Robust Aggregation in High Dimensions
Sarthak Choudhary, Aashish Kolluri, Prateek Saxena
High Dimension Biased Datasets Defense Algorithm Byzantine Robust Aggregation Robust Aggregator

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

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 14, 2023

Client-side Gradient Inversion Against Federated Learning from Poisoning
Jiaheng Wei, Yanjun Zhang, Leo Yu Zhang, Chao Chen, Shirui Pan, Kok-Leong Ong, Jun Zhang, Yang Xiang
Poisoning Attack Gradient Inversion Attack Byzantine Robust Aggregation Client Gradient

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

February 20, 2023

ByzSecAgg: A Byzantine-Resistant Secure Aggregation Scheme for Federated Learning Based on Coded Computing and Vector Commitment
Tayyebeh Jahani-Nezhad, Mohammad Ali Maddah-Ali, Giuseppe Caire
Secure Aggregation Secret Sharing Secure Computation Byzantine Robust Aggregation Commitment Mechanism Coded Computing

February 14, 2023

An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learning
Shenghui Li, Edith C. -H. Ngai, Thiemo Voigt
Experimental Study Byzantine Robust Byzantine Attack Robust Aggregation Byzantine Robust Aggregation

February 12, 2023

Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization
Hamidreza Almasi, Harsh Mishra, Balajee Vamanan, Sathya N. Ravi
Training Data Potential Scalability Convex Optimization Convergence Guarantee Subspace Learning Country Recognition Planning Loss Byzantine Robust Aggregation Byzantine Failure One Shot Aggregation

October 29, 2022

Security-Preserving Federated Learning via Byzantine-Sensitive Triplet Distance
Youngjoon Lee, Sangwoo Park, Joonhyuk Kang
Contrastive Learning Byzantine Robust Byzantine Attack Byzantine Robust Federated Learning Byzantine Robust Aggregation Edge Computing Device

July 16, 2022

MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attacks
Ali Ramezani-Kebrya, Iman Tabrizian, Fartash Faghri, Petar Popovski
Robust Learning Byzantine Robust Adversarial Agent Aggregated Gradient Byzantine Robust Aggregation Targeted Attack

Byzantine Robust Aggregation

Papers

PFAttack: Stealthy Attack Bypassing Group Fairness in Federated Learning

Byzantine-Robust Aggregation for Securing Decentralized Federated Learning

Impact of Network Topology on Byzantine Resilience in Decentralized Federated Learning

BadSampler: Harnessing the Power of Catastrophic Forgetting to Poison Byzantine-robust Federated Learning

Byzantine-Resilient Secure Aggregation for Federated Learning Without Privacy Compromises

Robust Federated Learning Mitigates Client-side Training Data Distribution Inference Attacks

Towards Fair, Robust and Efficient Client Contribution Evaluation in Federated Learning

Attacking Byzantine Robust Aggregation in High Dimensions

AGRAMPLIFIER: Defending Federated Learning Against Poisoning Attacks Through Local Update Amplification

BRFL: A Blockchain-based Byzantine-Robust Federated Learning Model

Client-side Gradient Inversion Against Federated Learning from Poisoning

Practical Differentially Private and Byzantine-resilient Federated Learning

ByzSecAgg: A Byzantine-Resistant Secure Aggregation Scheme for Federated Learning Based on Coded Computing and Vector Commitment

An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learning

Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization

Security-Preserving Federated Learning via Byzantine-Sensitive Triplet Distance

MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attacks