SUPERVOICE: Text-Independent Speaker Verification Using Ultrasound Energy in Human Speech

@article{Guo2022SUPERVOICETS,
  title={SUPERVOICE: Text-Independent Speaker Verification Using Ultrasound Energy in Human Speech},
  author={Hanqing Guo and Qiben Yan and Nikolay Ivanov and Ying Zhu and Li Xiao and Eric J. Hunter},
  journal={Proceedings of the 2022 ACM on Asia Conference on Computer and Communications Security},
  year={2022}
}
  • Hanqing GuoQiben Yan E. Hunter
  • Published 28 May 2022
  • Computer Science
  • Proceedings of the 2022 ACM on Asia Conference on Computer and Communications Security
Voice-activated systems are integrated into a variety of desktop, mobile, and Internet-of-Things (IoT) devices. However, voice spoofing attacks, such as impersonation and replay attacks, in which malicious attackers synthesize the voice of a victim or simply replay it, have brought growing security concerns. Existing speaker verification techniques distinguish individual speakers via the spectrographic features extracted from an audible frequency range of voice commands. However, they often… 

References

SHOWING 1-10 OF 53 REFERENCES

The Catcher in the Field: A Fieldprint based Spoofing Detection for Text-Independent Speaker Verification

The key insight of CaField is to construct "fieldprint'' with the acoustic biometrics embedded in sound fields, i.e., a physical field of acoustic energy created as the sound propagates over the air, as analogous to "voiceprint''.

Preventing replay attacks on speaker verification systems

A system for detecting spoofing attacks on speaker verification systems and shows the degradation on the speaker verification performance in the presence of this kind of attack and how to use the spoofing detection to mitigate that degradation.

Hearing Your Voice is Not Enough: An Articulatory Gesture Based Liveness Detection for Voice Authentication

This work proposes VoiceGesture, a liveness detection system for replay attack detection on smartphones that detects a live user by leveraging both the unique articulatory gesture of the user when speaking a passphrase and the mobile audio hardware advances.

An assessment of automatic speaker verification vulnerabilities to replay spoofing attacks

Experiments show that low-effort replay attacks present at least a comparable threat to speech synthesis and voice conversion, and a relatively new approach based on the local binary pattern analysis of speech spectrograms is shown to outperform a competing approach based upon the detection of far-field recordings.

VoiceLive: A Phoneme Localization based Liveness Detection for Voice Authentication on Smartphones

Results show that VoiceLive is robust to different phone placements and is compatible to different sampling rates and phone models, and uses such unique TDoA dynamic which doesn't exist under replay attacks for liveness detection.

Continuous Authentication for Voice Assistants

VAuth is the first system that provides continuous authentication for voice assistants, designed to fit in widely-adopted wearable devices, where it collects body-surface vibrations of the user and matches it with the speech signal received by the voice assistant's microphone.

Robust Speaker Recognition from Distant Speech under Real Reverberant Environments Using Speaker Embeddings

Three different speaker recognition systems ranging from a traditional universal background model (UBM) i-vector system to a state-of-the-art deep neural network (DNN) speaker embedding system with a probabilistic linear discriminant analysis (PLDA) back-end are characterized.

SurfingAttack: Interactive Hidden Attack on Voice Assistants Using Ultrasonic Guided Waves

A new attack called SurfingAttack is designed that would enable multiple rounds of interactions between the voice-controlled device and the attacker over a longer distance and without the need to be in line-of-sight, and enables new attack scenarios, such as hijacking a mobile Short Message Service passcode, making ghost fraud calls without owners’ knowledge, etc.

Void: A fast and light voice liveness detection system

Void detects voice spoofing attacks using the differences in spectral power between live-human voices and voices replayed through speakers, and is resilient against hidden voicecommand, inaudible voice command, voice synthesis, equalization manipulation attacks, and combining replay attacks with live- human voices.

DolphinAttack: Inaudible Voice Commands

A totally inaudible attack, DolphinAttack, that modulates voice commands on ultrasonic carriers to achieve inaudibility and is validated on popular speech recognition systems, including Siri, Google Now, Samsung S Voice, Huawei HiVoice, Cortana and Alexa.
...