Robust Aggregation

Robust aggregation in machine learning focuses on combining predictions or model updates from multiple sources, even when some are unreliable or malicious. Current research emphasizes developing algorithms that are resilient to various attacks, such as Byzantine failures, selfish clients, and backdoor poisoning, often employing techniques like geometric median, trimmed mean, and adaptive weighting schemes to filter out or downweight faulty inputs. This field is crucial for securing distributed learning paradigms like federated learning, enhancing their reliability and applicability in sensitive domains such as healthcare and finance, where data privacy and model integrity are paramount.

Papers

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

July 22, 2024

Tackling Selfish Clients in Federated Learning
Andrea Augello, Ashish Gupta, Giuseppe Lo Re, Sajal K. Das
Robust Aggregation

July 17, 2024

Individualized Federated Learning for Traffic Prediction with Error Driven Aggregation
Hang Chen, Collin Meese, Mark Nejad, Chien-Chung Shen
Personalized Federated Learning Traffic Prediction Traffic Forecasting Traffic Management Traffic Network Traffic Pattern Robust Aggregation

June 30, 2024

A Whole-Process Certifiably Robust Aggregation Method Against Backdoor Attacks in Federated Learning
Anqi Zhou, Yezheng Liu, Yidong Chai, Hongyi Zhu, Xinyue Ge, Yuanchun Jiang, Meng Wang
Native Robustness Backdoor Attack Robust Aggregation

June 19, 2024

The Surprising Benefits of Base Rate Neglect in Robust Aggregation
Yuqing Kong, Shu Wang, Ying Wang
Robust Aggregation Low Regret Surprising Effectiveness Forecast Aggregation Base Rate

May 31, 2024

Pursuing Overall Welfare in Federated Learning through Sequential Decision Making
Seok-Ju Hahn, Gi-Soo Kim, Junghye Lee
Federated Learning Online Convex Optimization Sequential Decision Making Robust Aggregation Social Welfare Fairness Aware Aggregation Seller Side Outcome Fairness

May 24, 2024

RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation
Peihua Mai, Ran Yan, Yan Pang
Federated Learning Poisoning Attack Secure Aggregation Robust Aggregation Robust Federated Learning Secret Sharing

May 23, 2024

The Vital Role of Gradient Clipping in Byzantine-Resilient Distributed Learning
Youssef Allouah, Rachid Guerraoui, Nirupam Gupta, Ahmed Jellouli, Geovani Rizk, John Stephan
Native Robustness Gradient Descent Robust Version Distributed Learning Robust Aggregation State of the Art Robustness Truly Robust Case

October 25, 2023

Robust and Actively Secure Serverless Collaborative Learning
Olive Franzese, Adam Dziedzic, Christopher A. Choquette-Choo, Mark R. Thomas, Muhammad Ahmad Kaleem, Stephan Rabanser, Congyu Fang, Somesh Jha, Nicolas Papernot, Xiao Wang
Robust Version Collaborative Machine Learning Malicious Client Robust Aggregation

October 5, 2023

Fishnets: Information-Optimal, Scalable Aggregation for Sets and Graphs
T. Lucas Makinen, Justin Alsing, Benjamin D. Wandelt
Graph Neural Network Graph Drawing Tiny Set Robust Aggregation Convolutional Counterpart Optimal Embeddings

August 21, 2023

Federated Learning Robust to Byzantine Attacks: Achieving Zero Optimality Gap
Shiyuan Zuo, Rongfei Fan, Han Hu, Ning Zhang, Shimin Gong
Byzantine Attack Linear Convergence Robust Aggregation Optimality Gap Robust Federated Learning

August 14, 2023

DISBELIEVE: Distance Between Client Models is Very Essential for Effective Local Model Poisoning Attacks
Indu Joshi, Priyank Upadhya, Gaurav Kumar Nayak, Peter Schüffler, Nassir Navab
Distance Matter Client Model Robust Aggregation

May 16, 2023

Smart Policy Control for Securing Federated Learning Management System
Aditya Pribadi Kalapaaking, Ibrahim Khalil, Mohammed Atiquzzaman
Federated Learning Smart Contract Robust Aggregation

April 27, 2023

Attacks on Robust Distributed Learning Schemes via Sensitivity Curve Maximization
Christian A. Schroth, Stefan Vlaski, Abdelhak M. Zoubir
Decentralized Learning New Attack Data Aggregation Distributed Learning Robust Aggregation Mean Aggregation

March 20, 2023

Recursive Euclidean Distance Based Robust Aggregation Technique For Federated Learning
Charuka Herath, Yogachandran Rahulamathavan, Xiaolan Liu
Local Model Robust Aggregation Euclidean Distance Local Update

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

May 22, 2022

Robust Quantity-Aware Aggregation for Federated Learning
Jingwei Yi, Fangzhao Wu, Huishuai Zhang, Bin Zhu, Tao Qi, Guangzhong Sun, Xing Xie
Quantity Aware Robust Aggregation

May 5, 2022

Over-The-Air Federated Learning under Byzantine Attacks
Houssem Sifaou, Geoffrey Ye Li
Air Federated Learning Air Computation Byzantine Attack Robust Aggregation

April 6, 2022

Consensual Aggregation on Random Projected High-dimensional Features for Regression
Sothea Has
Novel Regression Cross Validation Random Projection Robust Aggregation High Dimensional Feature Fairness Aware Aggregation

April 3, 2022

Byzantine-Robust Federated Linear Bandits
Ali Jadbabaie, Haochuan Li, Jian Qian, Yi Tian
Linear Bandit O$ Regret Robust Aggregation Federated Bandit

Robust Aggregation

Papers

Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregation

Tackling Selfish Clients in Federated Learning

Individualized Federated Learning for Traffic Prediction with Error Driven Aggregation

A Whole-Process Certifiably Robust Aggregation Method Against Backdoor Attacks in Federated Learning

The Surprising Benefits of Base Rate Neglect in Robust Aggregation

Pursuing Overall Welfare in Federated Learning through Sequential Decision Making

RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation

The Vital Role of Gradient Clipping in Byzantine-Resilient Distributed Learning

Robust and Actively Secure Serverless Collaborative Learning

Fishnets: Information-Optimal, Scalable Aggregation for Sets and Graphs

Federated Learning Robust to Byzantine Attacks: Achieving Zero Optimality Gap

DISBELIEVE: Distance Between Client Models is Very Essential for Effective Local Model Poisoning Attacks

Smart Policy Control for Securing Federated Learning Management System

Attacks on Robust Distributed Learning Schemes via Sensitivity Curve Maximization

Recursive Euclidean Distance Based Robust Aggregation Technique For Federated Learning

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

Robust Quantity-Aware Aggregation for Federated Learning

Over-The-Air Federated Learning under Byzantine Attacks

Consensual Aggregation on Random Projected High-dimensional Features for Regression

Byzantine-Robust Federated Linear Bandits