Data Poisoning against Differentially-Private Learners: Attacks and Defenses

Abstract

Data poisoning attacks aim to manipulate the model produced by a learning algorithm by adversarially modifying the training set. We consider differential privacy as a defensive measure against this type of attack. We show that private learners are resistant to data poisoning attacks when the adversary is only able to poison a small number of items. However, this protection degrades as the adversary is allowed to poison more data. We emprically evaluate this protection by designing attack algorithms targeting objective and output perturbation learners, two standard approaches to differentially-private machine learning. Experiments show that our methods are effective when the attacker is allowed to poison sufficiently many training items.