Minimum Noticeable Difference based Adversarial Privacy Preserving Image Generation. (arXiv:2206.08638v1 [cs.CV])

Deep learning models are found to be vulnerable to adversarial examples, as
wrong predictions can be caused by small perturbation in input for deep
learning models. Most of the existing works of adversarial image generation try
to achieve attacks for most models, while few of them make efforts on
guaranteeing the perceptual quality of the adversarial examples. High quality
adversarial examples matter for many applications, especially for the privacy
preserving. In this work, we develop a framework based on the …

arxiv cv difference generation image image generation privacy