Silent Killer: A Stealthy, Clean-Label, Black-Box Backdoor Attack

TMLR Paper2298 Authors

Abstract: Backdoor poisoning attacks pose a well-known risk to neural networks. However, most studies have focused on lenient threat models. We introduce Silent Killer, a novel attack that operates in clean-label, black-box settings, uses a stealthy poison and trigger and outperforms existing methods. We investigate the use of universal adversarial perturbations as triggers in clean-label attacks, following the success of such approaches under poison-label settings. We analyze the success of a naive adaptation and find that gradient alignment for crafting the poison is required to ensure high success rates. We conduct thorough experiments on MNIST, CIFAR10, and a reduced version of ImageNet and achieve state-of-the-art results.

Submission Length: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Yaoliang_Yu1

Submission Number: 2298