Score: 0

Whisper Smarter, not Harder: Adversarial Attack on Partial Suppression

Published: July 30, 2025 | arXiv ID: 2508.09994v2

By: Zheng Jie Wong, Bingquan Shen

Potential Business Impact:

Makes voice assistants safer from sneaky tricks.

Currently, Automatic Speech Recognition (ASR) models are deployed in an extensive range of applications. However, recent studies have demonstrated the possibility of adversarial attack on these models which could potentially suppress or disrupt model output. We investigate and verify the robustness of these attacks and explore if it is possible to increase their imperceptibility. We additionally find that by relaxing the optimisation objective from complete suppression to partial suppression, we can further decrease the imperceptibility of the attack. We also explore possible defences against these attacks and show a low-pass filter defence could potentially serve as an effective defence.

Country of Origin
πŸ‡ΈπŸ‡¬ Singapore

Page Count
14 pages

Category
Computer Science:
Sound