Sharpness-Aware Data Poisoning Attack

arXiv:2305.14851v2 Announce Type: replace
Abstract: Recent research has highlighted the vulnerability of Deep Neural Networks (DNNs) against data poisoning attacks. These attacks aim to inject poisoning samples into the models' training dataset such that the trained models have inference failures. While previous studies have executed different types of attacks, one major challenge that greatly limits their effectiveness is the uncertainty of the re-training process after the injection of poisoning samples, including the re-training initialization or algorithms. To address this challenge, …

aim arxiv attack attacks aware challenge cs.cr data data poisoning dataset failures inject major networks neural networks poisoning poisoning attacks research studies training types vulnerability