Detecting Replay Attacks Using Multi-Channel Audio: A Neural Network-Based Method
Sound
2020-07-07 v3 Cryptography and Security
Machine Learning
Audio and Speech Processing
Abstract
With the rapidly growing number of security-sensitive systems that use voice as the primary input, it becomes increasingly important to address these systems' potential vulnerability to replay attacks. Previous efforts to address this concern have focused primarily on single-channel audio. In this paper, we introduce a novel neural network-based replay attack detection model that further leverages spatial information of multi-channel audio and is able to significantly improve the replay attack detection performance.
Cite
@article{arxiv.2003.08225,
title = {Detecting Replay Attacks Using Multi-Channel Audio: A Neural Network-Based Method},
author = {Yuan Gong and Jian Yang and Christian Poellabauer},
journal= {arXiv preprint arXiv:2003.08225},
year = {2020}
}
Comments
Code of this work is available here: https://github.com/YuanGongND/multichannel-antispoof