Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Malacopula: adversarial automatic speaker verification attacks using a neural-based generalised Hammerstein model

About

We present Malacopula, a neural-based generalised Hammerstein model designed to introduce adversarial perturbations to spoofed speech utterances so that they better deceive automatic speaker verification (ASV) systems. Using non-linear processes to modify speech utterances, Malacopula enhances the effectiveness of spoofing attacks. The model comprises parallel branches of polynomial functions followed by linear time-invariant filters. The adversarial optimisation procedure acts to minimise the cosine distance between speaker embeddings extracted from spoofed and bona fide utterances. Experiments, performed using three recent ASV systems and the ASVspoof 2019 dataset, show that Malacopula increases vulnerabilities by a substantial margin. However, speech quality is reduced and attacks can be detected effectively under controlled conditions. The findings emphasise the need to identify new vulnerabilities and design defences to protect ASV systems from adversarial attacks in the wild.

Massimiliano Todisco, Michele Panariello, Xin Wang, H\'ector Delgado, Kong Aik Lee, Nicholas Evans• 2024

Related benchmarks

TaskDatasetResultRank
Audio Spoof DetectionPartialSpoof (PS) (test)
EER5.898
22
Fake DetectionPartialSpoof (dev)
EER3.022
12
Showing 2 of 2 rows

Other info

Follow for update