Invertible Image Dataset Protection
This addresses data security for companies in AI applications, offering a novel defense mechanism against model piracy, though it appears incremental as it builds on adversarial example techniques.
The paper tackles the problem of protecting proprietary image datasets from unauthorized use by malicious actors, proposing a reversible adversarial example generator (RAEG) that transforms images to fool pirated models while maintaining performance for authorized ones, with experiments showing it provides better protection with slight distortion compared to previous methods.
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.