Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

HopSkipJumpAttack: A Query-Efficient Decision-Based Attack

About

The goal of a decision-based adversarial attack on a trained model is to generate adversarial examples based solely on observing output labels returned by the targeted model. We develop HopSkipJumpAttack, a family of algorithms based on a novel estimate of the gradient direction using binary information at the decision boundary. The proposed family includes both untargeted and targeted attacks optimized for $\ell_2$ and $\ell_\infty$ similarity metrics respectively. Theoretical analysis is provided for the proposed algorithms and the gradient direction estimate. Experiments show HopSkipJumpAttack requires significantly fewer model queries than Boundary Attack. It also achieves competitive performance in attacking several widely-used defense mechanisms. (HopSkipJumpAttack was named Boundary Attack++ in a previous version of the preprint.)

Jianbo Chen, Michael I. Jordan, Martin J. Wainwright• 2019

Related benchmarks

TaskDatasetResultRank
Object Hallucination EvaluationPOPE--
935
Black-box AttackLSUN
ASR95.8
189
Black-box AttackGenImage
ASR99.2
162
Adversarial AttackILSVRC 2012 (val)
Median L2 Distance24.181
112
Adversarial AttackILSVRC 2012
Median L2 Distance17.75
96
Adversarial AttackImageNet-21K (val)
Median L2 Distance4.367
80
Adversarial AttackTiny ImageNet (val)
Median L2 Distance0.959
64
Adversarial AttackImageNet 21k (test)
Median L2 Distance16.244
64
Untargeted AttackImageNet (test)
Mean L2 Distortion (2K Budget)44.53
42
Targeted AttackImageNet (test)
Mean L2 Distortion (2K Budget)50.96
38
Showing 10 of 18 rows

Other info

Follow for update