Detecting Replay Attacks Using Multi-Channel Audio: A Neural Network-Based Method

03/18/2020
by   Yuan Gong, et al.
0

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.

READ FULL TEXT
research
04/13/2019

Towards Vulnerability Analysis of Voice-Driven Interfaces and Countermeasures for Replay

Fake audio detection is expected to become an important research area in...
research
03/19/2021

Selectively Delaying Instructions to Prevent Microarchitectural Replay Attacks

MicroScope, and microarchitectural replay attacks in general, take advan...
research
04/05/2020

Security Analysis and Fault Detection Against Stealthy Replay Attacks

This paper investigates the security issue of the data replay attacks on...
research
09/01/2020

When the Differences in Frequency Domain are Compensated: Understanding and Defeating Modulated Replay Attacks on Automatic Speech Recognition

Automatic speech recognition (ASR) systems have been widely deployed in ...
research
02/16/2020

Multi-Task Siamese Neural Network for Improving Replay Attack Detection

Automatic speaker verification systems are vulnerable to audio replay at...
research
10/31/2018

Attentive Filtering Networks for Audio Replay Attack Detection

An attacker may use a variety of techniques to fool an automatic speaker...
research
07/26/2021

UR Channel-Robust Synthetic Speech Detection System for ASVspoof 2021

In this paper, we present UR-AIR system submission to the logical access...

Please sign up or login with your details

Forgot password? Click here to reset