paper-with-me

홈 › Papers

Abnormal Client Behavior Detection in Federated Learning

2019-10-22 · Suyi Li, Yong Cheng, Yang Liu, Wei Wang, Tianjian Chen

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.

📄 PDF Abstract BibTeX arXiv:1910.09933

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly DetectionFederated Learningimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Anomalous Client Detection in Federated Learning

2024-11-03 · Dipanwita Thakur, Antonella Guzzo, Giancarlo Fortino

Federated learning (FL), with the growing IoT and edge computing, is seen as a promising solution for applications that are latency- and privacy-aware. However, due to the widespread dispersion of data across many client…

Anomaly DetectionEdge-computingFederated Learning

FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in FL

2025-02-23 · Ehsan Hallaji, Roozbeh Razavi-Far, Mehrdad Saif

Federated learning systems are increasingly threatened by data poisoning attacks, where malicious clients compromise global models by contributing tampered updates. Existing defenses often rely on impractical assumptions…

Data PoisoningFederated Learning

FedTADBench: Federated Time-Series Anomaly Detection Benchmark

2022-12-19 · Fanxing Liu, Cheng Zeng, Le Zhang, Yingjie Zhou 외

Time series anomaly detection strives to uncover potential abnormal behaviors and patterns from temporal data, and has fundamental significance in diverse application scenarios. Constructing an effective detection model …

Anomaly DetectionFederated LearningTime SeriesTime Series Analysis+1

Abnormal Local Clustering in Federated Learning

2022-08-26 · Jihwan Won

Federated learning is a model for privacy without revealing private data by transfer models instead of personal and private data from local client devices. While, in the global model, it's crucial to recognize each local…

ClusteringFederated Learning

Anomaly Detection via Federated Learning

2022-10-12 · Marc Vucovich, Amogh Tarcar, Penjo Rebelo, Narendra Gade 외

Machine learning has helped advance the field of anomaly detection by incorporating classifiers and autoencoders to decipher between normal and anomalous behavior. Additionally, federated learning has provided a way for …

Anomaly DetectionFederated LearningIntrusion Detection