Pith. sign in

REVIEW 1 cited by

Boosting Adversarial Transferability through Enhanced Momentum

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

arxiv 2103.10609 v1 pith:3DA57YYW submitted 2021-03-19 cs.CV

classification cs.CV
keywords adversarialtransferabilitymethodsattackaveragegradientiterativemodels
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Deep learning models are known to be vulnerable to adversarial examples crafted by adding human-imperceptible perturbations on benign images. Many existing adversarial attack methods have achieved great white-box attack performance, but exhibit low transferability when attacking other models. Various momentum iterative gradient-based methods are shown to be effective to improve the adversarial transferability. In what follows, we propose an enhanced momentum iterative gradient-based method to further enhance the adversarial transferability. Specifically, instead of only accumulating the gradient during the iterative process, we additionally accumulate the average gradient of the data points sampled in the gradient direction of the previous iteration so as to stabilize the update direction and escape from poor local maxima. Extensive experiments on the standard ImageNet dataset demonstrate that our method could improve the adversarial transferability of momentum-based methods by a large margin of 11.1% on average. Moreover, by incorporating with various input transformation methods, the adversarial transferability could be further improved significantly. We also attack several extra advanced defense models under the ensemble-model setting, and the enhancements are remarkable with at least 7.8% on average.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attack

    cs.LG 2024-11 conditional novelty 4.0 of 10

    TARL replaces Triangle Attack's fixed angle-update rule with a Q-learning policy, reporting comparable attack success on ImageNet and CIFAR-10 with 500 queries instead of 1,000.

Pith tools