English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Voice biometrics is drawing increasing attention as it is a promisingalternative to legacy passwords for user authentication. Recently, a growingbody of work shows that voice biometrics is vulnerable to spoofing throughreplay attacks, where an adversary tries to spoof voice authentication systemsby using a pre-recorded voice sample collected from a genuine user. To thisend, we propose VoiceGesture, a liveness detection solution for voiceauthentication on smart devices such as smartphones and smart speakers.VoiceGesture detects a live user by leveraging both the unique articulatorygesture of the user when speaking a passphrase and the audio hardware advanceson these smart devices. Specifically, our system re-uses a pair of built-inspeaker and microphone on a smart device as a Doppler radar, which transmits ahigh-frequency acoustic sound from the speaker and listens to the reflectionsat the microphone when a user speaks a passphrase. Then we extract Dopplershifts resulted from the user's articulatory gestures for liveness detection.VoiceGesture is practical as it requires neither cumbersome operations noradditional hardware but a speaker and a microphone commonly available on smartdevices that support voice input. Our experimental evaluation with 21participants and different smart devices shows that VoiceGesture achieves over99% and around 98% detection accuracy for text-dependent and text-independentliveness detection, respectively. Results also show that VoiceGesture is robustto different device placements, low audio sampling frequency, and supportsmedium range liveness detection on smart speakers in various use scenarios likesmart homes and smart vehicles.

A Continuous Liveness Detection for Voice Authentication on Smart Devices