all InfoSec news
Enrollment-stage Backdoor Attacks on Speaker Recognition Systems via Adversarial Ultrasound. (arXiv:2306.16022v1 [cs.SD])
cs.CR updates on arXiv.org arxiv.org
Automatic Speaker Recognition Systems (SRSs) have been widely used in voice
applications for personal identification and access control. A typical SRS
consists of three stages, i.e., training, enrollment, and recognition. Previous
work has revealed that SRSs can be bypassed by backdoor attacks at the training
stage or by adversarial example attacks at the recognition stage. In this
paper, we propose TUNER, a new type of backdoor attack against the enrollment
stage of SRS via adversarial ultrasound modulation, which is inaudible, …
access access control adversarial applications attacks automatic backdoor backdoor attacks control identification personal recognition stage systems training ultrasound voice work