Face Encryption via Frequency-Restricted Identity-Agnostic Attacks. (arXiv:2308.05983v1 [cs.CV])

Billions of people are sharing their daily live images on social media
everyday. However, malicious collectors use deep face recognition systems to
easily steal their biometric information (e.g., faces) from these images. Some
studies are being conducted to generate encrypted face photos using adversarial
attacks by introducing imperceptible perturbations to reduce face information
leakage. However, existing studies need stronger black-box scenario feasibility
and more natural visual appearances, which challenge the feasibility of privacy
protection. To address these problems, we propose …

adversarial adversarial attacks attacks biometric daily encrypted encryption face recognition identity images information live malicious media people photos recognition restricted sharing social social media steal studies systems