Geometrically Adaptive Dictionary Attack on Face Recognition
Junyoung Byun, Hyojun Go, Changick Kim

TL;DR
This paper introduces GADA, a novel, query-efficient black-box attack method on face recognition systems that leverages 3D face alignment and UV texture mapping to improve attack efficiency and evade detection.
Contribution
The paper proposes GADA, a new attack strategy that enhances query efficiency and robustness against detection by exploiting face geometry and previous perturbations.
Findings
GADA significantly reduces the number of queries needed for successful attacks.
It improves attack success rates on LFW and CPLFW datasets.
GADA can bypass query similarity-based detection methods.
Abstract
CNN-based face recognition models have brought remarkable performance improvement, but they are vulnerable to adversarial perturbations. Recent studies have shown that adversaries can fool the models even if they can only access the models' hard-label output. However, since many queries are needed to find imperceptible adversarial noise, reducing the number of queries is crucial for these attacks. In this paper, we point out two limitations of existing decision-based black-box attacks. We observe that they waste queries for background noise optimization, and they do not take advantage of adversarial perturbations generated for other images. We exploit 3D face alignment to overcome these limitations and propose a general strategy for query-efficient black-box attacks on face recognition named Geometrically Adaptive Dictionary Attack (GADA). Our core idea is to create an adversarial…
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.
Videos
Geometrically Adaptive Dictionary Attack on Face Recognition· youtube
Taxonomy
TopicsAdversarial Robustness in Machine Learning
