The Hidden Adversarial Vulnerabilities of Medical Federated Learning

Erfan Darzi, Florian Dubost, Nanna. M. Sijtsema, P. M. A van Ooijen
10/21/2023
cs.LGcs.AI

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

In this paper, we delve into the susceptibility of federated medical image analysis systems to adversarial attacks. Our analysis uncovers a novel exploitation avenue: using gradient information from prior global model updates, adversaries can enhance the efficiency and transferability of their attacks. Specifically, we demonstrate that single-step attacks (e.g. FGSM), when aptly initialized, can outperform the efficiency of their iterative counterparts but with reduced computational demand. Our findings underscore the need to revisit our understanding of AI security in federated healthcare settings.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Adversarially-Aware Architecture Design for Robust Medical AI Systems

86% match2025

MedFedPure: A Medical Federated Framework with MAE-based Detection and Diffusion Purification for Inference-Time Attacks

85% match2025

Shadow defense against gradient inversion attack in federated learning

85% match1 repo32025

Adversarial Robustness Analysis of Vision-Language Models in Medical Image Segmentation

84% match2025

Mitigating Adversarial Attacks in Federated Learning with Trusted Execution Environments

84% match1 repo42023

MedLeak: Multimodal Medical Data Leakage in Secure Federated Learning with Crafted Models

84% match2024

Cite this paper

@article{darzi2023hidden,
  title  = {The Hidden Adversarial Vulnerabilities of Medical Federated Learning},
  author = {Erfan Darzi and Florian Dubost and Nanna. M. Sijtsema and P. M. A van Ooijen},
  year   = {2023},
  eprint = {2310.13893},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.13893v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.13893.svg)](https://codeofpaper.com/paper/2310.13893)

Discussion