# Learning to Detect Malicious Clients for Robust Federated Learning Source: [Learning to Detect Malicious Clients for Robust Federated Learning]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:03:19.943Z Authors: Suyi Li, Yong Cheng, Wei Wang, Yang Liu, Tianjian Chen Published: 2020-02-01T14:09:48.000Z ## Abstract Federated learning systems are vulnerable to attacks from malicious clients. As the central server in the system cannot govern the behaviors of the clients, a rogue client may initiate an attack by sending malicious model updates to the server, so as to degrade the learning performance or enforce targeted model poisoning attacks (a.k.a. backdoor attacks). Therefore, timely detecting these malicious model updates and the underlying attackers becomes critically important. In this work, we propose a new framework for robust federated learning where the central server learns to detect and remove the malicious model updates using a powerful detection model, leading to targeted defense. We evaluate our solution in both image classification and sentiment analysis tasks with a variety of machine learning models. Experimental results show that our solution ensures robust federated learning that is resilient to both the Byzantine attacks and the targeted model poisoning attacks. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on FashionMNIST](): Image Classification; FashionMNIST; Accuracy: 73.1. - [Image Classification on CIFAR-100 (Standard)](): Image Classification; CIFAR-100; Accuracy: 15.5. - [Image Classification on CIFAR-10 (Accuracy)](): Image Classification; CIFAR-10; Accuracy: 47. ## Original sources and implementation [Original paper]() [PDF]()