DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection. (arXiv:2305.13625v1 [cs.CV])

The increasingly pervasive facial recognition (FR) systems raise serious
concerns about personal privacy, especially for billions of users who have
publicly shared their photos on social media. Several attempts have been made
to protect individuals from being identified by unauthorized FR systems
utilizing adversarial attacks to generate encrypted face images. However,
existing methods suffer from poor visual quality or low attack success rates,
which limit their utility. Recently, diffusion models have achieved tremendous
success in image generation. In this work, …

adversarial adversarial attacks attacks diffusion models facial facial recognition media personal photos privacy protect protection recognition serious social social media systems