Back to Search Start Over

Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion

Authors :
Souri, Hossein
Bansal, Arpit
Kazemi, Hamid
Fowl, Liam
Saha, Aniruddha
Geiping, Jonas
Wilson, Andrew Gordon
Chellappa, Rama
Goldstein, Tom
Goldblum, Micah
Publication Year :
2024

Abstract

Modern neural networks are often trained on massive datasets that are web scraped with minimal human inspection. As a result of this insecure curation pipeline, an adversary can poison or backdoor the resulting model by uploading malicious data to the internet and waiting for a victim to scrape and train on it. Existing approaches for creating poisons and backdoors start with randomly sampled clean data, called base samples, and then modify those samples to craft poisons. However, some base samples may be significantly more amenable to poisoning than others. As a result, we may be able to craft more potent poisons by carefully choosing the base samples. In this work, we use guided diffusion to synthesize base samples from scratch that lead to significantly more potent poisons and backdoors than previous state-of-the-art attacks. Our Guided Diffusion Poisoning (GDP) base samples can be combined with any downstream poisoning or backdoor attack to boost its effectiveness. Our implementation code is publicly available at: https://github.com/hsouri/GDP .

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2403.16365
Document Type :
Working Paper