Indiscriminate Data Poisoning Attacks on Neural Networks

arXiv:2204.09092v2 Announce Type: replace
Abstract: Data poisoning attacks, in which a malicious adversary aims to influence a model by injecting "poisoned" data into the training process, have attracted significant recent attention. In this work, we take a closer look at existing poisoning attacks and connect them with old and new algorithms for solving sequential Stackelberg games. By choosing an appropriate loss function for the attacker and optimizing with algorithms that exploit second-order information, we design poisoning attacks that are effective …

abstract algorithms arxiv attacks attention closer look cs.cr cs.lg data data poisoning influence look networks neural networks poisoning attacks process them training type work