Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning. (arXiv:2212.02582v1 [cs.LG])

Semi-supervised learning methods can train high-accuracy machine learning
models with a fraction of the labeled training samples required for traditional
supervised learning. Such methods do not typically involve close review of the
unlabeled training samples, making them tempting targets for data poisoning
attacks. In this paper we investigate the vulnerabilities of semi-supervised
learning methods to backdoor data poisoning attacks on the unlabeled samples.
We show that simple poisoning attacks that influence the distribution of the
poisoned samples' predicted labels are …

attacks backdoor data data poisoning poisoning