SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.00762 · 2022

Backdoor Attack is a Devil in Federated GAN-based Medical Image Synthesis

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep Learning-based image synthesis techniques have been applied in healthcare research for generating medical images to support open research. Training generative adversarial neural networks (GAN) usually requires large amounts of training data. Federated learning (FL) provides a way of training a central model using distributed data from different medical institutions while keeping raw data locally. However, FL is vulnerable to backdoor attack, an adversarial by poisoning training data, given the central server cannot access the original data directly. Most backdoor attack strategies focus on classification models and centralized domains. In this study, we propose a way of attacking federated GAN (FedGAN) by treating the discriminator with a commonly used data poisoning strategy in backdoor attack classification models. We demonstrate that adding a small trigger with size less than 0.5 percent of the original image size can corrupt the FL-GAN model. Based on the proposed attack, we provide two effective defense strategies: global malicious detection and local training regularization. We show that combining the two defense strategies yields a robust medical image generation.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2207.00762")
get_code_for_paper("2207.00762")
have("2207.00762")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2207.00762.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2207.00762.svg)](https://syntology.ai/paper/2207.00762)

Connect an agent — have() is free.