Malacopula: Adversarial Automatic Speaker Verification Attacks Using A Neural-based Generalised Hammerstein Model

Abstract

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.

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keytodisco2024malacopula

Related papers

• Malafide: A Novel Adversarial Convolutive Noise Attack Against Deepfake And Spoofing Detection Systems (2023)7.50
• Toward Improving Synthetic Audio Spoofing Detection Robustness Via Meta-learning And Disentangled Training With Adversarial Examples (2024)6.77
• Transforming Acoustic Characteristics To Deceive Playback Spoofing Countermeasures Of Speaker Verification Systems (2018)6.34
• A Comparative Study On Recent Neural Spoofing Countermeasures For Synthetic Speech Detection (2021)0.00
• Inaudible Adversarial Perturbations For Targeted Attack In Speaker Recognition (2020)12.33
• Generalizing Speaker Verification For Spoof Awareness In The Embedding Space (2024)7.16
• Adversarial Sample Detection For Speaker Verification By Neural Vocoders (2021)0.00
• Adversarial Defense For Deep Speaker Recognition Using Hybrid Adversarial Training (2020)9.59