4 papers
ErasableMask: A Robust and Erasable Privacy Protection Scheme against Black-box Face Recognition Models
Sipeng Shen, Yunming Zhang, Dengpan Ye +5
While face recognition (FR) models have brought remarkable convenience in face verification and identification, they also pose substantial privacy risks to the public. Existing fac…
Take Fake as Real: Realistic-like Robust Black-box Adversarial Attack to Evade AIGC Detection
Caiyun Xie, Dengpan Ye, Yunming Zhang +4
The security of AI-generated content (AIGC) detection is crucial for ensuring multimedia content credibility. To enhance detector security, research on adversarial attacks has beco…
StyleMark: A Robust Watermarking Method for Art Style Images Against Black-Box Arbitrary Style Transfer
Yunming Zhang, Dengpan Ye, Sipeng Shen +1
Arbitrary Style Transfer (AST) achieves the rendering of real natural images into the painting styles of arbitrary art style images, promoting art communication. However, misuse of…
DIP-Watermark: A Double Identity Protection Method Based on Robust Adversarial Watermark
Yunming Zhang, Dengpan Ye, Caiyun Xie +4
The wide deployment of Face Recognition (FR) systems poses privacy risks. One countermeasure is adversarial attack, deceiving unauthorized malicious FR, but it also disrupts regula…