RAEDiff: Denoising Diffusion Probabilistic Models Based Reversible Adversarial Examples Self-Generation and Self-Recovery. (arXiv:2311.12858v1 [cs.CR])

Collected and annotated datasets, which are obtained through extensive
efforts, are effective for training Deep Neural Network (DNN) models. However,
these datasets are susceptible to be misused by unauthorized users, resulting
in infringement of Intellectual Property (IP) rights owned by the dataset
creators. Reversible Adversarial Exsamples (RAE) can help to solve the issues
of IP protection for datasets. RAEs are adversarial perturbed images that can
be restored to the original. As a cutting-edge approach, RAE scheme can serve
the purposes …

adversarial creators dataset datasets intellectual property network neural network property recovery rights training