.png){kind=icon}
Return
PSO-Based Closed Box Adversarial Patch Attack Against Face Recognition
.png){kind=icon}
PRE
AI
DOI：10.1109/tcsvt.2026.3680540.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Deep Neural Networks (DNNs) are vulnerable to adversarial patch attacks, which raises security concerns for face recognition systems using DNNs. Previous adversarial patch generation methods typically optimize perturbations in regions that maximally influence critical facial features. However, these existing methods are mostly limited to fixed shapes such as rectangles or squares. This confines subsequent patch texture optimization within these quadrilaterals, resulting in suboptimal adaptation to the complex geometric shapes of critical facial features, which may limit the effectiveness and transferability of the adversarial attacks. To address this issue, this paper proposes a PSO-based Adversarial Patch (PAP) method to generate a dynamic patch to be injected into the face. In the proposed PAP, by employing Particle Swarm Optimization (PSO) with adversarial similarity as the objective, the algorithm searches within a base circle to determine the optimal shape and position of the pre-defined patch. This approach enables the patch to exhibit extrapolation of polygonal deformations, ensuring that the patch optimally balances location, texture, and geometry, which enhances the adversarial transferability of the patch. To evaluate the vulnerability of face recognition models, we explore impersonation attacks under the closed box setting. Extensive experiments show that the proposed PAP improves attack performance across various face recognition models and datasets. Moreover, PAP achieves better transferability on commercial face recognition systems than existing methods.
Keywords:
Feeds
Circuits and systems
Circuits
Feedback
Optical noise
Videos
Impersonation attacks
Video equipment
Pixel
Electronic mail
Adversarial patch
face recognition
impersonation attack
shape extrapolation
Journal
IF:
11.1
Papers:
869
Citations:
3.1W
Organization
Cited Papers
No cited papers available