REVIEW 1 cited by
Silent Killer: A Stealthy, Clean-Label, Black-Box Backdoor Attack
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 1 Pith paper
-
When Forgetting Triggers Backdoors: A Clean Unlearning Attack
A clean-label backdoor hidden across multiple classes is activated and amplified by unlearning clean samples, reaching attack success above 90 percent after forgetting.
Discussion (0). Continue with ORCID to comment.