Unraveling Adversarial Examples against Speaker Identification -- Techniques for Attack Detection and Victim Model Classification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916142284537856 |
|---|---|
| author | Joshi, Sonal Thebaud, Thomas Villalba, Jesús Dehak, Najim |
| author_facet | Joshi, Sonal Thebaud, Thomas Villalba, Jesús Dehak, Najim |
| contents | Adversarial examples have proven to threaten speaker identification systems, and several countermeasures against them have been proposed. In this paper, we propose a method to detect the presence of adversarial examples, i.e., a binary classifier distinguishing between benign and adversarial examples. We build upon and extend previous work on attack type classification by exploring new architectures. Additionally, we introduce a method for identifying the victim model on which the adversarial attack is carried out. To achieve this, we generate a new dataset containing multiple attacks performed against various victim models. We achieve an AUC of 0.982 for attack detection, with no more than a 0.03 drop in performance for unknown attacks. Our attack classification accuracy (excluding benign) reaches 86.48% across eight attack types using our LightResNet34 architecture, while our victim model classification accuracy reaches 72.28% across four victim models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_19355 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unraveling Adversarial Examples against Speaker Identification -- Techniques for Attack Detection and Victim Model Classification Joshi, Sonal Thebaud, Thomas Villalba, Jesús Dehak, Najim Sound Cryptography and Security Machine Learning Audio and Speech Processing Adversarial examples have proven to threaten speaker identification systems, and several countermeasures against them have been proposed. In this paper, we propose a method to detect the presence of adversarial examples, i.e., a binary classifier distinguishing between benign and adversarial examples. We build upon and extend previous work on attack type classification by exploring new architectures. Additionally, we introduce a method for identifying the victim model on which the adversarial attack is carried out. To achieve this, we generate a new dataset containing multiple attacks performed against various victim models. We achieve an AUC of 0.982 for attack detection, with no more than a 0.03 drop in performance for unknown attacks. Our attack classification accuracy (excluding benign) reaches 86.48% across eight attack types using our LightResNet34 architecture, while our victim model classification accuracy reaches 72.28% across four victim models. |
| title | Unraveling Adversarial Examples against Speaker Identification -- Techniques for Attack Detection and Victim Model Classification |
| topic | Sound Cryptography and Security Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2402.19355 |