Deep learning has achieved enormous success in various industrial applications. Companies do not want their valuable data to be stolen by malicious employees to train pirated models. Nor do they wish the data analyzed by the competitors after using them online. We propose a novel solution for dataset protection in this scenario by robustly and reversibly transform the images into adversarial images. We develop a reversible adversarial example generator (RAEG) that introduces slight changes to the images to fool traditional classification models. Even though malicious attacks train pirated models based on the defensed versions of the protected images, RAEG can significantly weaken the functionality of these models. Meanwhile, the reversibility of RAEG ensures the performance of authorized models. Extensive experiments demonstrate that RAEG can better protect the data with slight distortion against adversarial defense than previous methods.
@article{arxiv.2112.14420,
title = {Invertible Image Dataset Protection},
author = {Kejiang Chen and Xianhan Zeng and Qichao Ying and Sheng Li and Zhenxing Qian and Xinpeng Zhang},
journal= {arXiv preprint arXiv:2112.14420},
year = {2021}
}
Comments
Submitted to ICME 2022. Authors are from University of Science and Technology of China, Fudan University, China. A potential extended version of this work is under way