Detecting Adversarial Attacks On Audiovisual Speech Recognition

Understand

Adversarial attacks pose a threat to deep learning models.

• However, research on adversarial detection methods, especially in the multi-modal domain, is very limited.
• In this work, we propose an efficient and straightforward detection method based on the temporal correlation between audio and video streams.
• The main idea is that the correlation between audio and video in adversarial examples will be lower than benign examples due to added adversarial noise.