paper-with-me

홈 › Papers

Adversarial Attacks on GMM i-vector based Speaker Verification Systems

2019-11-08 · Xu Li, Jinghua Zhong, Xixin Wu, Jianwei Yu, Xunying Liu, Helen Meng

This work investigates the vulnerability of Gaussian Mixture Model (GMM) i-vector based speaker verification systems to adversarial attacks, and the transferability of adversarial samples crafted from GMM i-vector based systems to x-vector based systems. In detail, we formulate the GMM i-vector system as a scoring function of enrollment and testing utterance pairs. Then we leverage the fast gradient sign method (FGSM) to optimize testing utterances for adversarial samples generation. These adversarial samples are used to attack both GMM i-vector and x-vector systems. We measure the system vulnerability by the degradation of equal error rate and false acceptance rate. Experiment results show that GMM i-vector systems are seriously vulnerable to adversarial attacks, and the crafted adversarial samples prove to be transferable and pose threats to neuralnetwork speaker embedding based systems (e.g. x-vector systems).

📄 PDF Abstract BibTeX arXiv:1911.03078

Code (2)

lixucuhk/adversarial-attack-on-GMM-i-vector-based-speaker-verification-systems 공식 구현 pytorch
MindSpore-paper-code-3/code10/tree/main/GMMBN mindspore

Tasks

Speaker Verification

Similar Papers 제목 키워드 기반

On the Detection of Adaptive Adversarial Attacks in Speaker Verification Systems

2022-02-11 · Zesheng Chen

Speaker verification systems have been widely used in smart phones and Internet of things devices to identify legitimate users. In recent work, it has been shown that adversarial attacks, such as FAKEBOB, can work effect…

Speaker Verification

Dictionary Attacks on Speaker Verification

2022-04-24 · Mirko Marras, Pawel Korus, Anubhav Jain, Nasir Memon

In this paper, we propose dictionary attacks against speaker verification - a novel attack vector that aims to match a large fraction of speaker population by chance. We introduce a generic formulation of the attack that…

Speaker VerificationVoice Cloning

Fooling End-to-end Speaker Verification by Adversarial Examples

2018-01-10 · Felix Kreuk, Yossi Adi, Moustapha Cisse, Joseph Keshet

Automatic speaker verification systems are increasingly used as the primary means to authenticate costumers. Recently, it has been proposed to train speaker verification systems using end-to-end deep neural models. In th…

Speaker Verification

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

2024-08-17 · Massimiliano Todisco, Michele Panariello, Xin Wang, Héctor Delgado 외

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. U…

Adversarial AttackSpeaker Verification

Adversarial Attacks on Spoofing Countermeasures of automatic speaker verification

2019-10-19 · Songxiang Liu, Haibin Wu, Hung-Yi Lee, Helen Meng

High-performance spoofing countermeasure systems for automatic speaker verification (ASV) have been proposed in the ASVspoof 2019 challenge. However, the robustness of such systems under adversarial attacks has not been …

Speaker Verification