Title | ||
---|---|---|
Can We Use Speaker Recognition Technology To Attack Itself? Enhancing Mimicry Attacks Using Automatic Target Speaker Selection |
Abstract | ||
---|---|---|
We consider technology-assisted mimicry attacks in the context of automatic speaker verification ( ASV). We use ASV itself to select targeted speakers to be attacked by human-based mimicry. We recorded 6 naive mimics for whom we select target celebrities from VoxCeleb1 and VoxCeleb2 corpora ( 7,365 potential targets) using an i-vector system. The attacker attempts to mimic the selected target, with the utterances subjected to ASV tests using an independently developed x-vector system. Our main finding is negative: even if some of the attacker scores against the target speakers were slightly increased, our mimics did not succeed in spoofing the x-vector system. Interestingly, however, the relative ordering of the selected targets ( closest, furthest, median) are consistent between the systems, which suggests some level of transferability between the systems. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/icassp.2019.8683811 | 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) |
Keywords | Field | DocType |
Speaker verification, mimicry, spoofing | Speaker verification,Spoofing attack,Computer science,Speech recognition,Speaker recognition,Mimicry,Transferability | Journal |
Volume | ISSN | Citations |
abs/1811.03790 | 1520-6149 | 1 |
PageRank | References | Authors |
0.35 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tomi Kinnunen | 1 | 1323 | 86.67 |
Rosa González Hautamäki | 2 | 1 | 0.35 |
Ville Vestman | 3 | 29 | 6.42 |
Md. Sahidullah | 4 | 326 | 24.99 |