Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders

arXiv:2405.01460v1 Announce Type: new
Abstract: Unlearnable examples (UEs) seek to maximize testing error by making subtle modifications to training examples that are correctly labeled. Defenses against these poisoning attacks can be categorized based on whether specific interventions are adopted during training. The first approach is training-time defense, such as adversarial training, which can mitigate poisoning effects but is computationally intensive. The other approach is pre-training purification, e.g., image short squeezing, which consists of several simple compressions but often encounters challenges …

arxiv autoencoders cs.ai cs.cr cs.cv cs.lg examples rate