Going in Style: Audio Backdoors Through Stylistic Transformations
Stefanos Koffas, Luca Pajola, Stjepan Picek, Mauro Conti
Abstract
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.
Topics & Concepts
BackdoorComputer scienceGuitarDomain (mathematical analysis)Style (visual arts)Code (set theory)Speech recognitionComputer securityProgramming languageHistoryArchaeologyMathematical analysisSet (abstract data type)ManagementEconomicsMathematicsAdvanced Malware Detection TechniquesDigital Media Forensic DetectionMusic and Audio Processing