FAIC Attack

Recently, there has been increasing concern about the security of facial recognition systems, especially in the context of black-box attacks. As attackers continue to devise new ways to exploit vulnerabilities, attention to the estimation of age in facial images becomes critical. Age estimation is also a critical task for a variety of applications, evolving with advances in computer vision and deep learning. In this paper, an identity-constrained face age against watermark attack (FAIC) method based on the DDE algorithm is proposed. The method finds the optimal solution to add watermarks by changing the position, size, transparency, and rotation angle of the watermark in the host image to deceive deep neural networks. In addition, we also try to constrain the face identity in the attack to achieve the effect of only changing the face age without changing the face identity after the attack.A series of experiments show that our method can improve the stability of face identity while attacking face age and improve the success rate of attack.

Recommended citation: [https://wangxiankang.github.io/files/ICMVA_2024_paper11.pdf]