Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Replay attack detection method of voice certification system

A voice authentication and replay attack technology, applied in the field of voice authentication technology and security, can solve the problems of microphone and speaker quality influence, low detection accuracy, etc., and achieve the effect of simple method, low algorithm complexity, and low delay.

Active Publication Date: 2019-09-06
ZHEJIANG UNIV
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of detection method usually has the characteristics of low detection accuracy and is greatly affected by the quality of microphones and speakers used in replay attacks
However, no research has focused on the distortion of the speech signal caused by the change of the diaphragm motion pattern on the hardware path of the attack device.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Replay attack detection method of voice certification system
  • Replay attack detection method of voice certification system
  • Replay attack detection method of voice certification system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] image 3 Among them, the upper channel is the live authentication voice signal obtained by the voice authentication system, and the lower channel is the voice signal obtained by HiVi audio replay attack. It can be clearly seen that the positive polarity ratio of the live voice signal is much higher than the negative polarity ratio, while the replay attack signal is just the opposite. After the first two steps of the detection method (voice activity detection, polarity index calculation), the polarity index of the live body authentication voice signal can be calculated to be 0.583, which is obviously greater than the polarity index of the replay attack voice signal, which is 0.494.

Embodiment 2

[0050] In this embodiment, the in vivo authentication voices of a total of 20 people (14 men and 6 women) were collected, and 8 kinds of loudspeakers with a wide quality distribution including the aforementioned HiVi audio were used to carry out replay attacks. The judgment threshold is set to 0.52, that is, the speech with a polarity index greater than 0.52 is judged as a live speech. Anyway, when it is judged as a replay attack, the detection accuracy of the live speech is 93.2%, and the detection accuracy of the replay attack is 96.5%.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a replay attack detection method of a voice certification system based on time domain polarity of a voice signal. The voice signal is collected and recorded through the voice certification system; a positive polarity signal and a negative polarity signal of the voice signal are extracted; and the proportional relationship of the positive polarity signal and the negative polarity signal is compared to judge that the voice signal belongs to replay attack or live voice, specifically, if the positive and negative polarity part proportion difference is large and the positivepolarity signal proportion is higher than the negative polarity signal proportion, the replay attack is considered, and if the positive and negative polarity part proportion difference is large and the positive polarity signal proportion is not higher than the negative polarity signal proportion, the live voice is considered. The replay attack in the voice certification system can be accurately and effectively detected.

Description

technical field [0001] The invention belongs to the field of voice authentication technology and security technology, and in particular relates to a software processing method capable of detecting replay attacks aimed at a voice authentication system. Background technique [0002] The voice authentication system is a security authentication system that uses voice authentication technology to extract the specific characteristics of the speaker's voice, and then identifies the identity of the speaker through voice feature pattern matching. Due to its low hardware requirements, low cost, simple and convenient authentication, and long-distance non-contact authentication, it has gradually become a mainstream user authentication and access control method. However, existing voice authentication systems are generally vulnerable to replay attacks. [0003] The replay attack against the voice authentication system refers to that the attacker pre-records and collects real legal user v...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G10L25/51
CPCG10L25/51
Inventor 冀晓宇龙颜徐文渊闫琛
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products