{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:11:05Z","timestamp":1750219865004,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T00:00:00Z","timestamp":1670544000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,12,9]]},"DOI":"10.1145\/3577530.3577574","type":"proceedings-article","created":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T22:13:24Z","timestamp":1680214404000},"page":"278-283","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Decision-based adversarial attack for speaker recognition models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0178-2502","authenticated-orcid":false,"given":"Xueyang","family":"Cao","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, University of Jinan, China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8620-9766","authenticated-orcid":false,"given":"Shanshan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, University of Jinan, China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4948-3803","authenticated-orcid":false,"given":"Zhenxiang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, University of Jinan, China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6132-4805","authenticated-orcid":false,"given":"Xiaoqing","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, University of Jinan, China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9682-6573","authenticated-orcid":false,"given":"Weiliang","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, University of Jinan, China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1099-4649","authenticated-orcid":false,"given":"Yadi","family":"Han","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, University of Jinan, China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,3,30]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"4072","article-title":"An overview of automatic speaker recognition technology[C]\/\/2002 IEEE international conference on acoustics, speech, and signal processing","volume":"4","author":"Reynolds D A","year":"2002","unstructured":"Reynolds D A . An overview of automatic speaker recognition technology[C]\/\/2002 IEEE international conference on acoustics, speech, and signal processing . IEEE , 2002 , 4 : IV- 4072 -IV-4075. Reynolds D A. An overview of automatic speaker recognition technology[C]\/\/2002 IEEE international conference on acoustics, speech, and signal processing. IEEE, 2002, 4: IV-4072-IV-4075.","journal-title":"IEEE"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.004"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.11591\/ijece.v8i5.pp2804-2811"},{"key":"e_1_3_2_1_4_1","volume-title":"Msu-avis dataset: Fusing face and voice modalities for biometric recognition in indoor surveillance videos[C]\/\/2018 24th International Conference on Pattern Recognition (ICPR)","author":"Chowdhury A","year":"2018","unstructured":"Chowdhury A , Atoum Y , Tran L , Msu-avis dataset: Fusing face and voice modalities for biometric recognition in indoor surveillance videos[C]\/\/2018 24th International Conference on Pattern Recognition (ICPR) . IEEE , 2018 : 3567-3573. Chowdhury A, Atoum Y, Tran L, Msu-avis dataset: Fusing face and voice modalities for biometric recognition in indoor surveillance videos[C]\/\/2018 24th International Conference on Pattern Recognition (ICPR). IEEE, 2018: 3567-3573."},{"key":"e_1_3_2_1_5_1","volume-title":"Secure smart home: A voiceprint and internet based authentication system for remote accessing[C]\/\/2016 11th International Conference on Computer Science & Education (ICCSE)","author":"Ren H","year":"2016","unstructured":"Ren H , Song Y , Yang S , Secure smart home: A voiceprint and internet based authentication system for remote accessing[C]\/\/2016 11th International Conference on Computer Science & Education (ICCSE) . IEEE , 2016 : 247-251. Ren H, Song Y, Yang S, Secure smart home: A voiceprint and internet based authentication system for remote accessing[C]\/\/2016 11th International Conference on Computer Science & Education (ICCSE). IEEE, 2016: 247-251."},{"key":"e_1_3_2_1_6_1","volume-title":"Inaudible adversarial perturbations for targeted attack in speaker recognition[J]. arXiv preprint arXiv:2005.10637","author":"Wang Q","year":"2020","unstructured":"Wang Q , Guo P , Xie L. Inaudible adversarial perturbations for targeted attack in speaker recognition[J]. arXiv preprint arXiv:2005.10637 , 2020 . Wang Q, Guo P, Xie L. Inaudible adversarial perturbations for targeted attack in speaker recognition[J]. arXiv preprint arXiv:2005.10637, 2020."},{"key":"e_1_3_2_1_7_1","first-page":"1962","article-title":"Fooling end-to-end speaker verification with adversarial examples[C]\/\/2018 IEEE international conference on acoustics, speech and signal processing (ICASSP)","volume":"2018","author":"Kreuk F","unstructured":"Kreuk F , Adi Y , Cisse M , Fooling end-to-end speaker verification with adversarial examples[C]\/\/2018 IEEE international conference on acoustics, speech and signal processing (ICASSP) . IEEE , 2018 : 1962 - 1966 . Kreuk F, Adi Y, Cisse M, Fooling end-to-end speaker verification with adversarial examples[C]\/\/2018 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, 2018: 1962-1966.","journal-title":"IEEE"},{"key":"e_1_3_2_1_8_1","volume-title":"Crafting adversarial examples for speech paralinguistics applications[J]. arXiv preprint arXiv:1711.03280","author":"Gong Y","year":"2017","unstructured":"Gong Y , Poellabauer C. Crafting adversarial examples for speech paralinguistics applications[J]. arXiv preprint arXiv:1711.03280 , 2017 . Gong Y, Poellabauer C. Crafting adversarial examples for speech paralinguistics applications[J]. arXiv preprint arXiv:1711.03280, 2017."},{"key":"e_1_3_2_1_9_1","volume-title":"Who is real bob? adversarial attacks on speaker recognition systems[C]\/\/2021 IEEE Symposium on Security and Privacy (SP)","author":"Chen G","year":"2021","unstructured":"Chen G , Chenb S , Fan L , Who is real bob? adversarial attacks on speaker recognition systems[C]\/\/2021 IEEE Symposium on Security and Privacy (SP) . IEEE , 2021 : 694-711. Chen G, Chenb S, Fan L, Who is real bob? adversarial attacks on speaker recognition systems[C]\/\/2021 IEEE Symposium on Security and Privacy (SP). IEEE, 2021: 694-711."},{"key":"e_1_3_2_1_10_1","volume-title":"Li J","author":"Du T","year":"2020","unstructured":"Du T , Ji S , Li J , Sirenattack : Generating adversarial audio for end-to-end acoustic systems[C]\/\/Proceedings of the 15th ACM Asia Conference on Computer and Communications Security . 2020 : 357-369. Du T, Ji S, Li J, Sirenattack: Generating adversarial audio for end-to-end acoustic systems[C]\/\/Proceedings of the 15th ACM Asia Conference on Computer and Communications Security. 2020: 357-369."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Zheng B Jiang P Wang Q Black-box adversarial attacks on commercial speech platforms with minimal information[C]\/\/Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security. 2021: 86-107.  Zheng B Jiang P Wang Q Black-box adversarial attacks on commercial speech platforms with minimal information[C]\/\/Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security. 2021: 86-107.","DOI":"10.1145\/3460120.3485383"},{"key":"e_1_3_2_1_12_1","volume-title":"One-to-one Example-based Automatic Image Coloring Using Deep Convolutional Generative Adversarial Network[J]. Journal of Advances in Information Technology Vol","author":"Seo J","year":"2017","unstructured":"Seo J , Yoon T , Kim J , One-to-one Example-based Automatic Image Coloring Using Deep Convolutional Generative Adversarial Network[J]. Journal of Advances in Information Technology Vol , 2017 , 8(2). Seo J, Yoon T, Kim J, One-to-one Example-based Automatic Image Coloring Using Deep Convolutional Generative Adversarial Network[J]. Journal of Advances in Information Technology Vol, 2017, 8(2)."},{"volume-title":"PMLR","author":"Kumar A","key":"e_1_3_2_1_13_1","unstructured":"Kumar A , Irsoy O , Ondruska P , Ask me anything: Dynamic memory networks for natural language processing[C]\/\/International conference on machine learning . PMLR , 2016: 1378-1387. Kumar A, Irsoy O, Ondruska P, Ask me anything: Dynamic memory networks for natural language processing[C]\/\/International conference on machine learning. PMLR, 2016: 1378-1387."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Zhang Y Jiang Z Villalba J Black-Box Attacks on Spoofing Countermeasures Using Transferability of Adversarial Examples[C]\/\/INTERSPEECH. 2020: 4238-4242.  Zhang Y Jiang Z Villalba J Black-Box Attacks on Spoofing Countermeasures Using Transferability of Adversarial Examples[C]\/\/INTERSPEECH. 2020: 4238-4242.","DOI":"10.21437\/Interspeech.2020-2834"},{"key":"e_1_3_2_1_15_1","volume-title":"Liu J","author":"Li Z","year":"2020","unstructured":"Li Z , Wu Y , Liu J , Advpulse : Universal, synchronization-free, and targeted audio adversarial attacks via subsecond perturbations[C]\/\/Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security . 2020: 1121-1134. Li Z, Wu Y, Liu J, Advpulse: Universal, synchronization-free, and targeted audio adversarial attacks via subsecond perturbations[C]\/\/Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security. 2020: 1121-1134."},{"key":"e_1_3_2_1_16_1","volume-title":"Decision-based adversarial attacks: Reliable attacks against black-box machine learning models[J]. arXiv preprint arXiv:1712.04248","author":"Brendel W","year":"2017","unstructured":"Brendel W , Rauber J , Bethge M. Decision-based adversarial attacks: Reliable attacks against black-box machine learning models[J]. arXiv preprint arXiv:1712.04248 , 2017 . Brendel W, Rauber J, Bethge M. Decision-based adversarial attacks: Reliable attacks against black-box machine learning models[J]. arXiv preprint arXiv:1712.04248, 2017."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Dong Y Su H Wu B Efficient decision-based black-box adversarial attacks on face recognition[C]\/\/Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2019: 7714-7722.  Dong Y Su H Wu B Efficient decision-based black-box adversarial attacks on face recognition[C]\/\/Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2019: 7714-7722.","DOI":"10.1109\/CVPR.2019.00790"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Brunner T Diehl F Le M T Guessing smart: Biased sampling for efficient black-box adversarial attacks[C]\/\/Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2019: 4958-4966.  Brunner T Diehl F Le M T Guessing smart: Biased sampling for efficient black-box adversarial attacks[C]\/\/Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2019: 4958-4966.","DOI":"10.1109\/ICCV.2019.00506"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Shi Y Han Y Tian Q. Polishing decision-based adversarial noise with a customized sampling[C]\/\/Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020: 1030-1038.  Shi Y Han Y Tian Q. Polishing decision-based adversarial noise with a customized sampling[C]\/\/Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020: 1030-1038.","DOI":"10.1109\/CVPR42600.2020.00111"},{"key":"e_1_3_2_1_20_1","volume-title":"Prior convictions: Black-box adversarial attacks with bandits and priors[J]. arXiv preprint arXiv:1807.07978","author":"Ilyas A","year":"2018","unstructured":"Ilyas A , Engstrom L , Madry A. Prior convictions: Black-box adversarial attacks with bandits and priors[J]. arXiv preprint arXiv:1807.07978 , 2018 . Ilyas A, Engstrom L, Madry A. Prior convictions: Black-box adversarial attacks with bandits and priors[J]. arXiv preprint arXiv:1807.07978, 2018."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Li J Ji R Liu H Projection & probability-driven black-box attack[C]\/\/Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020: 362-371.  Li J Ji R Liu H Projection & probability-driven black-box attack[C]\/\/Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020: 362-371.","DOI":"10.1109\/CVPR42600.2020.00044"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Li J Ji R Chen P Aha! adaptive history-driven attack for decision-based black-box models[C]\/\/Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021: 16168-16177.  Li J Ji R Chen P Aha! adaptive history-driven attack for decision-based black-box models[C]\/\/Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021: 16168-16177.","DOI":"10.1109\/ICCV48922.2021.01586"},{"key":"e_1_3_2_1_23_1","volume-title":"SEC4SR: a security analysis platform for speaker recognition[J]. arXiv preprint arXiv:2109.01766","author":"Chen G","year":"2021","unstructured":"Chen G , Zhao Z , Song F , SEC4SR: a security analysis platform for speaker recognition[J]. arXiv preprint arXiv:2109.01766 , 2021 . Chen G, Zhao Z, Song F, SEC4SR: a security analysis platform for speaker recognition[J]. arXiv preprint arXiv:2109.01766, 2021."},{"key":"e_1_3_2_1_24_1","volume-title":"Speaker verification using adapted Gaussian mixture models[J]. Digital signal processing","author":"Reynolds D A","year":"2000","unstructured":"Reynolds D A , Quatieri T F , Dunn R B . Speaker verification using adapted Gaussian mixture models[J]. Digital signal processing , 2000 , 10(1-3): 19-41. Reynolds D A, Quatieri T F, Dunn R B. Speaker verification using adapted Gaussian mixture models[J]. Digital signal processing, 2000, 10(1-3): 19-41."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"e_1_3_2_1_26_1","first-page":"1021","article-title":"Speaker recognition from raw waveform with sincnet[C]\/\/2018 IEEE Spoken Language Technology Workshop (SLT)","volume":"2018","author":"Ravanelli M","unstructured":"Ravanelli M , Bengio Y . Speaker recognition from raw waveform with sincnet[C]\/\/2018 IEEE Spoken Language Technology Workshop (SLT) . IEEE , 2018 : 1021 - 1028 . Ravanelli M, Bengio Y. Speaker recognition from raw waveform with sincnet[C]\/\/2018 IEEE Spoken Language Technology Workshop (SLT). IEEE, 2018: 1021-1028.","journal-title":"IEEE"},{"key":"e_1_3_2_1_27_1","first-page":"5796","article-title":"Speaker recognition for multi-speaker conversations using x-vectors[C]\/\/ICASSP 2019-2019 IEEE International conference on acoustics, speech and signal processing (ICASSP)","volume":"2019","author":"Snyder D","unstructured":"Snyder D , Garcia-Romero D , Sell G , Speaker recognition for multi-speaker conversations using x-vectors[C]\/\/ICASSP 2019-2019 IEEE International conference on acoustics, speech and signal processing (ICASSP) . IEEE , 2019 : 5796 - 5800 . Snyder D, Garcia-Romero D, Sell G, Speaker recognition for multi-speaker conversations using x-vectors[C]\/\/ICASSP 2019-2019 IEEE International conference on acoustics, speech and signal processing (ICASSP). IEEE, 2019: 5796-5800.","journal-title":"IEEE"},{"key":"e_1_3_2_1_28_1","first-page":"1277","article-title":"A query-efficient decision-based attack[C]\/\/2020 ieee symposium on security and privacy (sp)","volume":"2020","author":"Chen J","unstructured":"Chen J , Jordan M I , Wainwright M J . Hopskipjumpattack : A query-efficient decision-based attack[C]\/\/2020 ieee symposium on security and privacy (sp) . IEEE , 2020 : 1277 - 1294 . Chen J, Jordan M I, Wainwright M J. Hopskipjumpattack: A query-efficient decision-based attack[C]\/\/2020 ieee symposium on security and privacy (sp). IEEE, 2020: 1277-1294.","journal-title":"IEEE"}],"event":{"name":"CSAI 2022: 2022 6th International Conference on Computer Science and Artificial Intelligence","acronym":"CSAI 2022","location":"Beijing China"},"container-title":["Proceedings of the 2022 6th International Conference on Computer Science and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577530.3577574","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3577530.3577574","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:35Z","timestamp":1750178855000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577530.3577574"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,9]]},"references-count":28,"alternative-id":["10.1145\/3577530.3577574","10.1145\/3577530"],"URL":"https:\/\/doi.org\/10.1145\/3577530.3577574","relation":{},"subject":[],"published":{"date-parts":[[2022,12,9]]},"assertion":[{"value":"2023-03-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}