2025
Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion Models
Nikolai Lund Kühne, Astrid H. F. Kitchena, Marie S. Jensen, Mikkel S. L. Brøndt, Martin Gonzalez, Christophe A. N. Biscio +1
ICASSP 2025accepted
Automatic speech recognition (ASR) systems are known to be vulnerable to adversarial attacks. This paper addresses detection and defence against targeted white-box attacks on speech signals for ASR systems. While existing work has utilised diffusion models (DMs) to purify adversarial examples, achie…