Salvato in:
Dettagli Bibliografici
Autori principali: Sayyafzadeh, Shahrzad, Chi, Hongmei, Bernadin, Shonda
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.09806
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908766631362560
author Sayyafzadeh, Shahrzad
Chi, Hongmei
Bernadin, Shonda
author_facet Sayyafzadeh, Shahrzad
Chi, Hongmei
Bernadin, Shonda
contents This work presents an end-to-end pipeline for generating, refining, and evaluating adversarial patches to compromise facial biometric systems, with applications in forensic analysis and security testing. We utilize FGSM to generate adversarial noise targeting an identity classifier and employ a diffusion model with reverse diffusion to enhance imperceptibility through Gaussian smoothing and adaptive brightness correction, thereby facilitating synthetic adversarial patch evasion. The refined patch is applied to facial images to test its ability to evade recognition systems while maintaining natural visual characteristics. A Vision Transformer (ViT)-GPT2 model generates captions to provide a semantic description of a person's identity for adversarial images, supporting forensic interpretation and documentation for identity evasion and recognition attacks. The pipeline evaluates changes in identity classification, captioning results, and vulnerabilities in facial identity verification and expression recognition under adversarial conditions. We further demonstrate effective detection and analysis of adversarial patches and adversarial samples using perceptual hashing and segmentation, achieving an SSIM of 0.95.
format Preprint
id arxiv_https___arxiv_org_abs_2601_09806
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Diffusion-Driven Deceptive Patches: Adversarial Manipulation and Forensic Detection in Facial Identity Verification
Sayyafzadeh, Shahrzad
Chi, Hongmei
Bernadin, Shonda
Computer Vision and Pattern Recognition
Artificial Intelligence
This work presents an end-to-end pipeline for generating, refining, and evaluating adversarial patches to compromise facial biometric systems, with applications in forensic analysis and security testing. We utilize FGSM to generate adversarial noise targeting an identity classifier and employ a diffusion model with reverse diffusion to enhance imperceptibility through Gaussian smoothing and adaptive brightness correction, thereby facilitating synthetic adversarial patch evasion. The refined patch is applied to facial images to test its ability to evade recognition systems while maintaining natural visual characteristics. A Vision Transformer (ViT)-GPT2 model generates captions to provide a semantic description of a person's identity for adversarial images, supporting forensic interpretation and documentation for identity evasion and recognition attacks. The pipeline evaluates changes in identity classification, captioning results, and vulnerabilities in facial identity verification and expression recognition under adversarial conditions. We further demonstrate effective detection and analysis of adversarial patches and adversarial samples using perceptual hashing and segmentation, achieving an SSIM of 0.95.
title Diffusion-Driven Deceptive Patches: Adversarial Manipulation and Forensic Detection in Facial Identity Verification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2601.09806