PhoneyTalker: An Out-of-the-Box Toolkit for Adversarial Example Attack on Speaker Recognition
Published in IEEE International Conference on Computer Communications (IEEE INFOCOM 2022), 2022
Recommended citation: Meng Chen, Li Lu*, Zhongjie Ba, Kui Ren. "PhoneyTalker: An Out-of-the-Box Toolkit for Adversarial Example Attack on Speaker Recognition." Proceedings of IEEE International Conference on Computer Communications (IEEE INFOCOM). London, United Kingdom. pp. 1419-1428. 2022. doi: 10.1109/INFOCOM48880.2022.9796934.
IEEE International Conference on Computer Communications is a top ranked international conference in computer networking and communication. IEEE INFOCOM is also a CCF-A conference. I am the corresponding author of this paper.
Abstract: Voice has become a fundamental method for human-computer interactions and person identification these days. Benefit from the rapid development of deep learning, speaker recognition exploiting voice biometrics has achieved great success in various applications. However, the shadow of adversarial example attacks on deep neural network-based speaker recognition recently raised extensive public concerns and enormous research interests. Although existing studies propose to generate adversarial examples by iterative optimization to deceive speaker recognition, these methods require multiple iterations to construct specific perturbations for a single voice, which is input-specific, time-consuming, and non-transferable, hindering the deployment and application for non-professional adversaries. In this paper, we propose PhoneyTalker, an out-of-the-box toolkit for any adversary to generate universal and transferable adversarial examples with low complexity, releasing the requirement for professional background and specialized equipment.