3 papers
eess.AS2025
A Study of the Removability of Speaker-Adversarial Perturbations
Liping Chen, Chenyang Guo, Kong Aik Lee +2
Recent advancements in adversarial attacks have demonstrated their effectiveness in misleading speaker recognition models, making wrong predictions about speaker identities. On the…
cs.SD2025
Any-to-any Speaker Attribute Perturbation for Asynchronous Voice Anonymization
Liping Chen, Chenyang Guo, Rui Wang +2
Speaker attribute perturbation offers a feasible approach to asynchronous voice anonymization by employing adversarially perturbed speech as anonymized output. In order to enhance…
cs.SD2024
On the Generation and Removal of Speaker Adversarial Perturbation for Voice-Privacy Protection
Chenyang Guo, Liping Chen, Zhuhai Li +3
Neural networks are commonly known to be vulnerable to adversarial attacks mounted through subtle perturbation on the input data. Recent development in voice-privacy protection has…