Adversarial Images through Stega Glasses
It addresses security vulnerabilities in computer vision systems, presenting an incremental approach by applying steganography to adversarial attacks.
This paper tackles the problem of creating adversarial images that are both visually and statistically undetectable by leveraging steganography, showing that steganography aids attackers more than defenders in fooling state-of-the-art classifiers.
This paper explores the connection between steganography and adversarial images. On the one hand, ste-ganalysis helps in detecting adversarial perturbations. On the other hand, steganography helps in forging adversarial perturbations that are not only invisible to the human eye but also statistically undetectable. This work explains how to use these information hiding tools for attacking or defending computer vision image classification. We play this cat and mouse game with state-of-art classifiers, steganalyzers, and steganographic embedding schemes. It turns out that steganography helps more the attacker than the defender.