RAEDiff: Denoising Diffusion Probabilistic Models Based Reversible Adversarial Examples Self-Generation and Self-Recovery
Year: 2023
Type: preprint
Abstract: 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 of preventing unauthorized users from engaging in malicious model training, as well as ensuring the legitimate usage of authorized users. Nevertheless, in the existing work, RAEs still rely on the embedded auxiliary information for restoration, which may compromise their adversarial abilities. In this paper, a novel self-generation and self-recovery method, named as RAEDiff, is introduced for generating RAEs based on a Denoising Diffusion Probabilistic Models (DDPM). It diffuses datasets into a Biased Gaussian Distribution (BGD) and utilizes the prior knowledge of the DDPM for generating and recovering RAEs. The experimental results demonstrate that RAEDiff effectively self-generates adversarial perturbations for DNN models, including Artificial Intelligence Generated Content (AIGC) models, while also exhibiting significant self-recovery capabilities.
Source: arXiv (Cornell University)
Authors: Xing, Fan, Zhou, Xiaoyi, Fan, Xuefeng, Tian, Zhuo, Zhao, Yan
Institution: Hainan University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4388964346