Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning

Marissa Catherine Connor, Vincent Emanuele

Keywords: data poisoning, backdoor attacks, semi-supervised learning

TL;DR: We investigate vulnerabilities of semi-supervised learning methods to backdoor data poisoning attacks in unlabeled data and identify characteristics necessary for attack success.

Abstract: 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 a simple poisoning attack using adversarially perturbed samples is highly effective - achieving an average attack success rate of 93.6%. We introduce a generalized attack framework targeting semi-supervised learning methods to better understand and exploit their limitations and to motivate future defense strategies.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning