Precision-Varying Prediction (PVP): Robustifying ASR Systems Against Adversarial Attacks
A preprint introduces Precision-Varying Prediction (PVP), a method that improves the adversarial robustness of automatic speech recognition (ASR) models by randomly varying the inference precision. The approach also enables adversarial example detection using a Gaussian classifier on outputs from different precision levels. When combined with uncertainty-based defenses, PVP increases the difficulty for adaptive attackers, requiring them to introduce more perceptible noise to evade detection. Experimental results show significant improvements in robustness and detection across multiple ASR models, languages, and attack types.
Why it matters: This work proposes a practical and effective defense against adversarial attacks on ASR systems, which are increasingly used in real-world automated applications.
Full story at: arXiv Audio and Speech Processing ↗