Paper ID | MLSP-10.1 | ||
Paper Title | HIGH-FREQUENCY ADVERSARIAL DEFENSE FOR SPEECH AND AUDIO | ||
Authors | Raphael Olivier, Bhiksha Raj, Muhammad Shah, Carnegie Mellon University, United States | ||
Session | MLSP-10: Deep Learning for Speech and Audio | ||
Location | Gather.Town | ||
Session Time: | Tuesday, 08 June, 16:30 - 17:15 | ||
Presentation Time: | Tuesday, 08 June, 16:30 - 17:15 | ||
Presentation | Poster | ||
Topic | Machine Learning for Signal Processing: [MLR-DEEP] Deep learning techniques | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | Recent work suggests that adversarial examples are enabled by high-frequency components in the dataset. In the speech domain where spectrograms are used extensively, masking those components seems like a sound direction for defenses against attacks. We explore a smoothing approach based on additive noise masking in priority high frequencies. We show that this approach is much more robust than the naive noise filtering approach, and a promising research direction. We successfully apply our defense on a Librispeech speaker identification task, and on the UrbanSound8K audio classification dataset. |