We demonstrate a novel audio-domain adversarial attack that modifies benign audio using a time-varying FIR filter. Unlike existing state-of-the-art attacks, our proposed method does not require a complex optimization procedure or generative model, relying only on a simple variant of gradient descent to tune filter parameters. In order to craft attacks that work well in real-world playback scenarios (“over-the-air”), we optimize through simulated distortions that mimic the properties of acoustic environments (e.g. reverb, noise, time-domain offset).
@inproceedings{oreilly2022filter,
title={Inconspicuous and effective over-the-air adversarial examples via adaptive filtering},
author={O'Reilly, Patrick and Awasthi, Pranjal and Vijayaragavan, Aravindan and Pardo, Bryan},
booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
year={2022}}