{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:13:58Z","timestamp":1783764838288,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819228584","type":"print"},{"value":"9789819228591","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:00:00Z","timestamp":1783814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:00:00Z","timestamp":1783814400000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-2859-1_23","type":"book-chapter","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:04:52Z","timestamp":1783764292000},"page":"312-328","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Audio Immunization Against Harmful Audio Editing with\u00a0Diffusion Models"],"prefix":"10.1007","author":[{"given":"Jing","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanqing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaoyang","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihang","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,12]]},"reference":[{"key":"23_CR1","unstructured":"Bhardwaj, R., Poria, S.: Red-teaming large language models using chain of utterances for safety-alignment. arXiv preprint arXiv:2308.09662 (2023)"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Carlini, N., Wagner, D.: Audio adversarial examples: targeted attacks on speech-to-text. In: 2018 IEEE Security and Privacy Workshops (SPW), pp.\u00a01\u20137 (2018)","DOI":"10.1109\/SPW.2018.00009"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Chen, S., Chen, L., Zhang, J., Lee, K., Ling, Z., Dai, L.: Adversarial speech for voice privacy protection from personalized speech generation. arXiv preprint arXiv:2401.11857 (2024)","DOI":"10.1109\/ICASSP48485.2024.10447699"},{"key":"23_CR4","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Advances in Neural Information Processing Systems, vol.\u00a034, pp. 8780\u20138794 (2021)"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Elizalde, B., Deshmukh, S., Al\u00a0Ismail, M., Wang, H.: Clap: learning audio concepts from natural language supervision. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"23_CR6","unstructured":"Fan, W., Chen, K., Liu, C., Zhang, W., Yu, N.: De-antifake: rethinking the protective perturbations against voice cloning attacks. arXiv preprint arXiv:2507.02606 (2025)"},{"key":"23_CR7","unstructured":"Ganguli, D., Lovitt, L., Kernion, J., Askell, A., Bai, Y., et\u00a0al.: Red teaming language models to reduce harms: methods, scaling behaviors, and lessons learned. arXiv preprint arXiv:2209.07858 (2022)"},{"key":"23_CR8","unstructured":"Ghai, O., Culbertson, T., Chi, E., Balasubramanian, N.: Harmful prompt classification for large language models. In: Proceedings of the ACM Workshop on Human-Centered Artificial Intelligence \u2013 Education and Practice (HCAIep) (2024)"},{"key":"23_CR9","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol.\u00a033, pp. 6840\u20136851 (2020)"},{"key":"23_CR10","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Huang, C.y., Lin, Y.Y., Lee, H.y., Lee, L.s.: Defending your voice: adversarial attack on voice conversion. In: 2021 IEEE Spoken Language Technology Workshop (SLT), pp. 552\u2013559. IEEE (2021)","DOI":"10.1109\/SLT48900.2021.9383529"},{"key":"23_CR12","unstructured":"Huynh, N.D., Bouadjenek, M.R., Razzak, I., Lee, K., Hassani, A., Zaslavsky, A.: Adversarial attacks on speech recognition systems for mission-critical applications: a survey. arXiv preprint arXiv:2202.10594 (2022)"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. In: Advances in Neural Information Processing Systems. arXiv:2206.00364 (2022)","DOI":"10.52202\/068431-1926"},{"key":"23_CR14","unstructured":"Kim, D., Kim, B., Lee, H., Kim, G.: Audiocaps: generating captions for audios in the wild. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 119\u2013132 (2019)"},{"key":"23_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2022.102526","volume":"127","author":"J Lan","year":"2022","unstructured":"Lan, J., Zhang, R., Yan, Z., Wang, J., Chen, Y., Hou, R.: Adversarial attacks and defenses in speaker recognition systems: A survey. J. Syst. Architect. 127, 102526 (2022)","journal-title":"J. Syst. Architect."},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Li, J., Ye, D., Tang, L., Chen, C., Hu, S.: Voice guard: protecting voice privacy with strong and imperceptible adversarial perturbation in the time domain. In: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, pp. 4812\u20134818 (2023)","DOI":"10.24963\/ijcai.2023\/535"},{"key":"23_CR17","unstructured":"Liu, H., et al.: AudioLDM: text-to-audio generation with latent diffusion models. In: Proceedings of the 40th International Conference on Machine Learning, vol.\u00a0202, pp. 21450\u201321474 (2023)"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Neekhara, P., Hussain, S., Pandey, P., Dubnov, S., McAuley, J., Koushanfar, F.: Universal adversarial perturbations for speech recognition systems. In: Proceedings of Interspeech, pp. 481\u2013485 (2019)","DOI":"10.21437\/Interspeech.2019-1353"},{"key":"23_CR19","unstructured":"Nichol, A., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: Proceedings of the 38th International Conference on Machine Learning, vol.\u00a0139, pp. 8162\u20138171 (2021)"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Perez, E., et al.: Red teaming language models with language models. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 3419\u20133448 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.225"},{"key":"23_CR21","unstructured":"Qin, Y., Carlini, N., Cottrell, G., Goodfellow, I., Raffel, C.: Imperceptible, robust, and targeted adversarial examples for automatic speech recognition. In: Proceedings of the 36th International Conference on Machine Learning, vol.\u00a097, pp. 5231\u20135240 (2019)"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Radharapu, B., Robinson, K., Aroyo, L., Lahoti, P.: AART: AI-assisted red-teaming with diverse data generation for new LLM-powered applications. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pp. 430\u2013442 (2023)","DOI":"10.18653\/v1\/2023.emnlp-industry.37"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"23_CR24","unstructured":"Salman, H., Khaddaj, A., Leclerc, G., Ilyas, A., Madry, A.: Raising the cost of malicious AI-powered image editing. In: Proceedings of the 40th International Conference on Machine Learning, vol.\u00a0202, pp. 29894\u201329918 (2023)"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nherr, L., Eisenhofer, T., Zeiler, S., Holz, T., Kolossa, D.: Imperio: robust over-the-air adversarial examples for automatic speech recognition systems. In: Annual Computer Security Applications Conference (ACSAC), pp. 843\u2013855 (2020)","DOI":"10.1145\/3427228.3427276"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Schramowski, P., Brack, M., Deiseroth, B., Kersting, K.: Safe latent diffusion: mitigating inappropriate degeneration in diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22522\u201322531 (2023)","DOI":"10.1109\/CVPR52729.2023.02157"},{"key":"23_CR27","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"23_CR28","unstructured":"Veaux, C., Yamagishi, J., MacDonald, K.: CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit. University of Edinburgh. The Centre for Speech Technology Research (CSTR) (2017)"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Weidinger, L., Uesato, J., Rauh, A., Huang, P., Glaese, A., et\u00a0al.: Taxonomy of risks posed by language models. In: ACM Conference on Fairness, Accountability, and Transparency (FAccT), pp. 214\u2013229 (2022)","DOI":"10.1145\/3531146.3533088"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Wu, Y., et\u00a0al.: Large-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (2023)","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Yakura, H., Sakuma, J.: Robust audio adversarial example for a physical attack. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI), pp. 5334\u20135341 (2019)","DOI":"10.24963\/ijcai.2019\/741"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Yu, Z., Zhai, S., Zhang, N.: Antifake: using adversarial audio to prevent unauthorized speech synthesis. In: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, pp. 460\u2013474. ACM (2023)","DOI":"10.1145\/3576915.3623209"},{"issue":"8","key":"23_CR33","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1038\/s42256-019-0080-x","volume":"1","author":"G Zeng","year":"2019","unstructured":"Zeng, G., Chen, Y., Cui, B., Yu, S.: Continuous learning of context-dependent processing in neural networks. Nature Mach. Intell. 1(8), 364\u2013372 (2019)","journal-title":"Nature Mach. Intell."},{"key":"23_CR34","unstructured":"Zhang, Z., et\u00a0al.: Safespeech: robust and universal voice protection against malicious speech synthesis. arXiv preprint arXiv:2504.09839 (2025)"},{"key":"23_CR35","unstructured":"Zhang, Z., et al.: Mitigating unauthorized speech synthesis for voice protection. arXiv preprint arXiv:2410.20742 (2024)"}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-2859-1_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:04:54Z","timestamp":1783764294000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-2859-1_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,12]]},"ISBN":["9789819228584","9789819228591"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-2859-1_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,12]]},"assertion":[{"value":"12 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","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":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ksem2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ksem2026.rosc.org.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}