DeepAI AI Chat
Log In Sign Up

Abnormal Client Behavior Detection in Federated Learning

by   Suyi Li, et al.

In federated learning systems, clients are autonomous in that their behaviors are not fully governed by the server. Consequently, a client may intentionally or unintentionally deviate from the prescribed course of federated model training, resulting in abnormal behaviors, such as turning into a malicious attacker or a malfunctioning client. Timely detecting those anomalous clients is therefore critical to minimize their adverse impacts. In this work, we propose to detect anomalous clients at the server side. In particular, we generate low-dimensional surrogates of model weight vectors and use them to perform anomaly detection. We evaluate our solution through experiments on image classification model training over the FEMNIST dataset. Experimental results show that the proposed detection-based approach significantly outperforms the conventional defense-based methods.


Learning to Detect Malicious Clients for Robust Federated Learning

Federated learning systems are vulnerable to attacks from malicious clie...

Anomaly Detection via Federated Learning

Machine learning has helped advance the field of anomaly detection by in...

Blockchain-based Federated Learning for Device Failure Detection in Industrial IoT

Device failure detection is one of most essential problems in industrial...

MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clients

Existing model poisoning attacks to federated learning assume that an at...

ABC-FL: Anomalous and Benign client Classification in Federated Learning

Federated Learning is a distributed machine learning framework designed ...

Navigation as the Attacker Wishes? Towards Building Byzantine-Robust Embodied Agents under Federated Learning

Federated embodied agent learning protects the data privacy of individua...