Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning
This addresses security risks in semi-supervised learning, which is widely used for efficiency, but the work is incremental as it builds on existing backdoor attack concepts.
The paper tackled the vulnerability of semi-supervised learning methods to backdoor data poisoning attacks on unlabeled samples, showing that simple attacks can achieve up to 96.9% success rate.
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 highly effective - achieving an average attack success rate as high as 96.9%. We introduce a generalized attack framework targeting semi-supervised learning methods to better understand and exploit their limitations and to motivate future defense strategies.