GreedyFool: Multi-Factor Imperceptibility and Its Application to Designing a Black-box Adversarial Attack
Hui Liu, Bo Zhao, Minzhi Ji, and Peng Liu

TL;DR
This paper introduces GreedyFool, a black-box adversarial attack leveraging a multi-factor perceptual metric, MulFactorLoss, which considers human visual system factors to generate more imperceptible adversarial examples with high success rates.
Contribution
It proposes a novel multi-factor perceptual metric, MulFactorLoss, and a black-box attack method, GreedyFool, that effectively creates imperceptible adversarial examples considering human visual perception.
Findings
MulFactorLoss outperforms existing pixelwise metrics in imperceptibility.
GreedyFool achieves a 100% success rate in black-box adversarial attacks.
Extensive experiments and user studies validate the effectiveness of the proposed methods.
Abstract
Adversarial examples are well-designed input samples, in which perturbations are imperceptible to the human eyes, but easily mislead the output of deep neural networks (DNNs). Existing works synthesize adversarial examples by leveraging simple metrics to penalize perturbations, that lack sufficient consideration of the human visual system (HVS), which produces noticeable artifacts. To explore why the perturbations are visible, this paper summarizes four primary factors affecting the perceptibility of human eyes. Based on this investigation, we design a multi-factor metric MulFactorLoss for measuring the perceptual loss between benign examples and adversarial ones. In order to test the imperceptibility of the multi-factor metric, we propose a novel black-box adversarial attack that is referred to as GreedyFool. GreedyFool applies differential evolution to evaluate the effects of…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Anomaly Detection Techniques and Applications · Integrated Circuits and Semiconductor Failure Analysis
