analiza aiqbench
This research addresses a critical vulnerability in face-recognition systems by introducing an efficient semantic attack framework suitable for robust adversarial training. By leveraging StyleGAN's latent space, the proposed method accelerates attack generation significantly while improving model resilience against unseen semantic perturbations like aging or pose shifts. The findings offer practical pathways to harden biometric authentication and surveillance models against computationally feasible adversarial edits.
StyleAT: Defending Face Recognition Against Semantic Attacks
arXiv:2609.23596v1 Announce Type: cross Abstract: With face-recognition models now embedded in everyday authentication and surveillance, recent works have pinpointed a critical weakness: these models remain acutely vulnerable to adversarial semantic edits. I.e., adversarially produced semantic alterations to the input, such as slight aging or pose changes, can induce misclassifications. Certain existing attacks are powerful, but they can be computationally costly, rendering them inadequate for developing defenses (e.g., through adversarial training). To fill the gap, we introduce BoundStyle, a potent semantic attack operating in StyleGAN's rich latent space to maximize misclassification rates. Notably, BoundStyle achieves high attack success rates while being ${\sim}{\times}9.5$ faster than existing state-of-the-art attacks, making it suitable for adversarial training. Building on BoundStyle, we develop StyleAT, an efficient adversarial training scheme that incorporates low-budget attack variants yet defends against stronger and unseen semantic attacks. We evaluate on two datasets unseen during training and seven models, and find that StyleAT boosts robust accuracy against state-of-the-art attacks and outperforms common defenses in various settings.
Abstract:With face-recognition models now embedded in everyday authentication and surveillance, recent works have pinpointed a critical weakness: these models remain acutely vulnerable to adversarial semantic edits. I.e., adversarially produced semantic alterations to the input, such as slight aging or pose changes, can induce misclassifications. Certain existing attacks are powerful, but they can be computationally costly, rendering them inadequate for developing defenses (e.g., through adversarial training). To fill the gap, we introduce BoundStyle, a potent semantic attack operating in StyleGAN's rich latent space to maximize misclassification rates. Notably, BoundStyle achieves high attack success rates while being ${\sim}{\times}9.5$ faster than existing state-of-the-art attacks, making it suitable for adversarial training. Building on BoundStyle, we develop StyleAT, an efficient adversarial training scheme that incorporates low-budget attack variants yet defends against stronger and unseen semantic attacks. We evaluate on two datasets unseen during training and seven models, and find that StyleAT boosts robust accuracy against state-of-the-art attacks and outperforms common defenses in various settings.
Accepted at the 37th British Machine Vision Conference (BMVC 2026), Lancaster, UK. 14 pages main text plus 13 pages of appendices, 15 figures, 12 tables
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Machine Learning (cs.LG)
arXiv:2609.23596 [cs.CV]
(or arXiv:2609.23596v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.23596 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 215 cuvinte
Subiecte conexe
Adv-TGD: Adversarial Text-Guided Diffusion for Face Recognition Impersonation Attacks
arXiv · 12 iun. 2026
DiffAttack: Evasion Attacks Against Face Recognition via Latent Diffusion Models
arXiv · 3 aug. 2026
FAS-R1: A Unified Multi-Task MLLM for Reasoning Face Anti-Spoofing
arXiv · 31 iul. 2026
SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing
arXiv · 16 sept. 2026