{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T08:32:18Z","timestamp":1743150738401,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819755905"},{"type":"electronic","value":"9789819755912"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-97-5591-2_32","type":"book-chapter","created":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T18:02:42Z","timestamp":1723572162000},"page":"373-385","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-layer Feature Augmentation Based Transferable Adversarial Examples Generation for Speaker Recognition"],"prefix":"10.1007","author":[{"given":"Zhuhai","family":"Li","sequence":"first","affiliation":[]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Wu","family":"Guo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,14]]},"reference":[{"key":"32_CR1","doi-asserted-by":"crossref","unstructured":"Xie, Y., Li, Z.: et al.: Enabling fast and universal audio adversarial attack using generative model. In: Proceeding AAAI Conference on Artificial Intelligence, pp. 14129\u201314137 (2021)","DOI":"10.1609\/aaai.v35i16.17663"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Generating high-quality adversarial examples with universal perturbation-based adaptive network and improved perceptual loss. In: Proceeding IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 10376\u201310380 (2024)","DOI":"10.1109\/ICASSP48485.2024.10446184"},{"key":"32_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LSP.2023.3236509","volume":"30","author":"J Yao","year":"2023","unstructured":"Yao, J., Chen, X., Zhang, X.L., et al.: Symmetric saliency-based adversarial attack to speaker identification. IEEE Signal Process. Lett. 30, 1\u20135 (2023)","journal-title":"IEEE Signal Process. Lett."},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Shamsabadi, A.S., Teixeira, F.S., Abad, A., et al.: FoolHD: Fooling speaker identification by highly imperceptible adversarial disturbances. In: Proceeding IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6159\u20136163 (2021)","DOI":"10.1109\/ICASSP39728.2021.9413760"},{"issue":"14","key":"32_CR5","doi-asserted-by":"publisher","first-page":"2183","DOI":"10.3390\/electronics11142183","volume":"11","author":"H Tan","year":"2022","unstructured":"Tan, H., Wang, L., Zhang, H., et al.: Adversarial attack and defense strategies of speaker recognition systems: a survey. Electronics 11(14), 2183 (2022)","journal-title":"Electronics"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Abdullah, H., Warren, K., Bindschaedler, V., et al.: Sok: The faults in our ASRs: an overview of attacks against automatic speech recognition and speaker identification systems. In: Proceeding IEEE Symposium on Security and Privacy, pp. 730\u2013747 (2021)","DOI":"10.1109\/SP40001.2021.00014"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Papernot, N., McDaniel, P., Goodfellow, I., et al.: Practical black-box attacks against machine learning. In: Proceeding ACM Asia Conference on Computer and Communications Security, pp. 506\u2013519 (2017)","DOI":"10.1145\/3052973.3053009"},{"key":"32_CR8","unstructured":"Liu, Y., Chen, X., Liu, C., Song, D.: Delving into transferable adversarial examples and black-box attacks. In: Proceeding International Conference on Learning Representations (2017)"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Dong, Y., Liao, F., et al.: Boosting adversarial attacks with momentum. In: Proceeding IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9185\u20139193 (2018)","DOI":"10.1109\/CVPR.2018.00957"},{"key":"32_CR10","unstructured":"Lin, J., Song, C., He, K., et al.: Nesterov accelerated gradient and scale invariance for adversarial attacks. In: Proceeding International Conference on Learning Representations (2020)"},{"key":"32_CR11","unstructured":"Kurakin, A., Goodfellow, I., Bengio, S.: Adversarial machine learning at scale. In: Proceeding International Conference on Learning Representations, pp. 1\u201317 (2017)"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Tan, H., Zhang, J., Zhang, H., et al.: NRI-FGSM: an efficient transferable adversarial attack method for speaker recognition system. In: Proceeding Interspeech, pp. 18\u201322 (2022)","DOI":"10.21437\/Interspeech.2022-10499"},{"key":"32_CR13","unstructured":"Nesterov, Y.: A method for unconstrained convex minimization problem with the rate of convergence O(1\/k2). In: Dokl. Akad. Nauk. SSSR, vol. 269, pp. 543\u2013547 (1983)"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Xie, C., Zhang, Z., Zhou, Y., et al.: Improving transferability of adversarial examples with input diversity. In: Proceeding IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2730\u20132739 (2019)","DOI":"10.1109\/CVPR.2019.00284"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Dong, Y., Pang, T., Su, H., Zhu, J.: Evading defenses to transferable adversarial examples by translation-invariant attacks. In: Proceding IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4312\u20134321 (2019)","DOI":"10.1109\/CVPR.2019.00444"},{"issue":"2","key":"32_CR16","doi-asserted-by":"publisher","first-page":"2332","DOI":"10.1007\/s10489-022-03469-5","volume":"53","author":"B Yang","year":"2023","unstructured":"Yang, B., Zhang, H., Li, Z., et al.: Adversarial example generation with adabelief optimizer and crop invariance. Appl. Intell. 53(2), 2332\u20132347 (2023)","journal-title":"Appl. Intell."},{"key":"32_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027","volume":"60","author":"A Nagrani","year":"2020","unstructured":"Nagrani, A., Chung, J.S., Xie, W., Zisserman, A.: Voxceleb: large-scale speaker verification in the wild. Comput. Speech Lang. 60, 101027 (2020)","journal-title":"Comput. Speech Lang."},{"key":"32_CR18","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.neunet.2021.03.004","volume":"140","author":"Z Bai","year":"2021","unstructured":"Bai, Z., Zhang, X.L.: Speaker recognition based on deep learning: An overview. Neural Netw. 140, 65\u201399 (2021)","journal-title":"Neural Netw."},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Chen, G., Chenb, S., Fan, L., et al.: Who is real bob? Adversarial attacks on speaker recognition systems. In: Proceeding IEEE Symposium on Security and Privacy, pp. 694\u2013711 (2021)","DOI":"10.1109\/SP40001.2021.00004"},{"key":"32_CR20","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/s40747-022-00782-x","volume":"9","author":"X Zhang","year":"2023","unstructured":"Zhang, X., Zhang, X., Sun, M., et al.: Imperceptible black-box waveform adversarial attack towards automatic speaker recognition. Complex & Intell. Syst. 9, 65\u201379 (2023)","journal-title":"Complex & Intell. Syst."},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Peddinti, V., Povey, D., Khudanpur, S.: A time delay neural network architecture for efficient modeling of long temporal contexts. In: Proceeding Interspeech, pp. 3214\u20133218 (2015)","DOI":"10.21437\/Interspeech.2015-647"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., et al.: Deep residual learning for image recognition. In: Proceeding IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., et al.: X-vectors: Robust DNN embeddings for speaker recognition. In: Proceeding IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5329\u20135333 (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Huh, J., Mun, S., et al.: In defence of metric learning for speaker recognition. In: Proceeding Interspeech, pp. 2977\u20132981 (2020)","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"32_CR25","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","volume":"43","author":"SH Gao","year":"2019","unstructured":"Gao, S.H., Cheng, M.M., Zhao, K., et al.: Res2Net: a new multi-scale backbone architecture. IEEE Trans. Pattern Anal. Mach. Intell. 43, 652\u2013662 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"32_CR26","doi-asserted-by":"crossref","unstructured":"Desplanques, B., Thienpondt, J., Demuynck, K.: ECAPA-TDNN: emphasized channel attention, propagation and aggregation in TDNN based speaker verification. In: Proceeding Interspeech, pp. 3830\u20133834 (2020)","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: additive angular margin loss for deep face recognition. In: Proceeding IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"32_CR28","unstructured":"Snyder, D., Chen, G., Povey, D.: MUSAN: a music, speech, and noise corpus. In: arXiv preprint arXiv:1510.08484 (2015)"},{"key":"32_CR29","doi-asserted-by":"crossref","unstructured":"Ko, T., Peddinti, V., Povey, D., et al.: A study on data augmentation of reverberant speech for robust speech recognition. In: Proceeding IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5220\u20135224 (2017)","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"32_CR30","doi-asserted-by":"crossref","unstructured":"Park, D.S., Chan, W., Zhang, Y., et al.: SpecAugment: a simple data augmentation method for automatic speech recognition. In: Proceeding Interspeech, pp. 2613\u20132617 (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Rix, A.W., et al.: Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs. In: Proceeding IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 749\u2013752 (2001)","DOI":"10.1109\/ICASSP.2001.941023"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5591-2_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T18:07:41Z","timestamp":1723572461000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5591-2_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819755905","9789819755912"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5591-2_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"14 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}