Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion

arXiv:2403.16365v1 Announce Type: cross
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 …

arxiv backdoors cs.cr cs.cv cs.lg