Voice Mimicry Attacks Assisted by Automatic Speaker Verification. (January 2020)

• Record Type: Journal Article
• Authors: Vestman, Ville; Kinnunen, Tomi; González Hautamäki, Rosa; Sahidullah, Md
• Is Part Of: Computer speech & language. Volume 59(2020)
• Page Start: 36
• Page End: 54
• Publication Date: 2020-01
• Subjects: Speaker verification -- Mimicry -- Crowdsourcing -- Spoofing -- Automatic target speaker selection -- Perceptual speaker similarity -- Prosody; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2019.05.005
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: Automatic speaker verification (ASV) to find targets for mimicry attacks. Attacker's ASV system differs from the attacked ASV system. Six locally recruited attackers, 7365 potential targets from VoxCeleb. Impersonators were not successful in attacking ASV systems. Broad rank of speakers generalizes from attacker's ASV to attacked ASV. Abstract: In this work, we simulate a scenario, where a publicly available ASV system is used to enhance mimicry attacks against another closed source ASV system. In specific, ASV technology is used to perform a similarity search between the voices of recruited attackers (6) and potential target speakers (7, 365) from VoxCeleb corpora to find the closest targets for each of the attackers. In addition, we consider 'median', 'furthest', and 'common' targets to serve as a reference points. Our goal is to gain insights how well similarity rankings transfer from the attacker's ASV system to the attacked ASV system, whether the attackers are able to improve their attacks by mimicking, and how the properties of the voices of attackers change due to mimicking. We address these questions through ASV experiments, listening tests, and prosodic and formant analyses. For the ASV experiments, we use i-vector technology in the attacker side, and x-vectors in the attacked side. For the listening tests, we recruit listeners through crowdsourcing. The results of the ASV experiments indicate that the speaker similarity scores transfer well from one ASV system to another. Both the ASV experiments and the listening tests reveal that the mimicry attempts do not, in general, help in bringing attacker's scores closer to the target's. A detailed analysis shows that mimicking does not improve attacks, when the natural voices of attackers and targets are similar to each other. The analysis of prosody and formants suggests that the attackers were able to considerably change their speaking rates when mimicking, but the changes in F0 and formants were modest. Overall, the results suggest that untrained impersonators do not pose a high threat towards ASV systems, but the use of ASV systems to attack other ASV systems is a potential threat.