Robust Audio Adversarial Example for a Physical Attack

Robust Audio Adversarial Example for a Physical Attack

Hiromu Yakura, Jun Sakuma

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
Main track. Pages 5334-5341. https://doi.org/10.24963/ijcai.2019/741

We propose a method to generate audio adversarial examples that can attack a state-of-the-art speech recognition model in the physical world. Previous work assumes that generated adversarial examples are directly fed to the recognition model, and is not able to perform such a physical attack because of reverberation and noise from playback environments. In contrast, our method obtains robust adversarial examples by simulating transformations caused by playback or recording in the physical world and incorporating the transformations into the generation process. Evaluation and a listening experiment demonstrated that our adversarial examples are able to attack without being noticed by humans. This result suggests that audio adversarial examples generated by the proposed method may become a real threat.
Keywords:
Natural Language Processing: Speech
Multidisciplinary Topics and Applications: Security and Privacy
Machine Learning: Deep Learning
Machine Learning: Adversarial Machine Learning