Exploring adversarial attacks in federated learning for medical imaging

TL;DR

This paper evaluates the vulnerabilities of federated learning in medical imaging against adversarial attacks, highlighting increased risks with domain-specific configurations and emphasizing the need for improved security measures.

Contribution

It provides a systematic assessment of adversarial attack vulnerabilities in federated medical imaging systems using domain-specific datasets.

Findings

Domain-specific configurations increase attack success rates

Current security protocols may be insufficient against adversarial threats

Highlights the need for robust defense mechanisms in federated medical imaging

Abstract

Federated learning offers a privacy-preserving framework for medical image analysis but exposes the system to adversarial attacks. This paper aims to evaluate the vulnerabilities of federated learning networks in medical image analysis against such attacks. Employing domain-specific MRI tumor and pathology imaging datasets, we assess the effectiveness of known threat scenarios in a federated learning environment. Our tests reveal that domain-specific configurations can increase the attacker's success rate significantly. The findings emphasize the urgent need for effective defense mechanisms and suggest a critical re-evaluation of current security protocols in federated medical image analysis systems.