Going In Style: Audio Backdoors Through Stylistic Transformations
This addresses security vulnerabilities in audio systems, presenting a novel attack method that is incremental in the field of adversarial machine learning.
The paper tackles the problem of backdoor attacks in audio by introducing stylistic triggers using guitar effects, achieving a 96% attack success rate.
This work explores stylistic triggers for backdoor attacks in the audio domain: dynamic transformations of malicious samples through guitar effects. We first formalize stylistic triggers - currently missing in the literature. Second, we explore how to develop stylistic triggers in the audio domain by proposing JingleBack. Our experiments confirm the effectiveness of the attack, achieving a 96% attack success rate. Our code is available in https://github.com/skoffas/going-in-style.