{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T16:49:28Z","timestamp":1761929368777,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819537280","type":"print"},{"value":"9789819537297","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-3729-7_23","type":"book-chapter","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T16:43:55Z","timestamp":1761929035000},"page":"275-288","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Stealthy Backdoor Attacks on\u00a0CLIP via\u00a0Stylistic Textual Triggers"],"prefix":"10.1007","author":[{"given":"Kun","family":"Cao","sequence":"first","affiliation":[]},{"given":"Bing","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Shengsheng","family":"Qian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,1]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: BadNL: backdoor attacks against NLP models with semantic-preserving improvements. In: Proceedings of the 37th Annual Computer Security Applications Conference, pp. 554\u2013569 (2021)","DOI":"10.1145\/3485832.3485837"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Conde, M.V., Turgutlu, K.: Clip-art: contrastive pre-training for fine-grained art classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3956\u20133960 (2021)","DOI":"10.1109\/CVPRW53098.2021.00444"},{"key":"23_CR3","doi-asserted-by":"publisher","first-page":"138872","DOI":"10.1109\/ACCESS.2019.2941376","volume":"7","author":"J Dai","year":"2019","unstructured":"Dai, J., Chen, C., Li, Y.: A backdoor attack against LSTM-based text classification systems. IEEE Access 7, 138872\u2013138878 (2019)","journal-title":"IEEE Access"},{"key":"23_CR4","unstructured":"Fang, H., Xiong, P., Xu, L., Chen, Y.: Clip2video: mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097 (2021)"},{"key":"23_CR5","unstructured":"Gao, K., et al.: Inducing high energy-latency of large vision-language models with verbose images. arXiv preprint arXiv:2401.11170 (2024)"},{"key":"23_CR6","first-page":"6704","volume":"35","author":"S Goel","year":"2022","unstructured":"Goel, S., et al.: Cyclip: cyclic contrastive language-image pretraining. Adv. Neural. Inf. Process. Syst. 35, 6704\u20136719 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR7","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International conference on machine learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Jia, J., Liu, Y., Gong, N.Z.: Badencoder: Backdoor attacks to pre-trained encoders in self-supervised learning. In: 2022 IEEE Symposium on Security and Privacy (SP), pp. 2043\u20132059. IEEE (2022)","DOI":"10.1109\/SP46214.2022.9833644"},{"key":"23_CR9","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of naacL-HLT, vol.\u00a01. Minneapolis, Minnesota (2019)"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Kurita, K., Michel, P., Neubig, G.: Weight poisoning attacks on pre-trained models. arXiv preprint arXiv:2004.06660 (2020)","DOI":"10.18653\/v1\/2020.acl-main.249"},{"key":"23_CR11","first-page":"1008","volume":"35","author":"J Lee","year":"2022","unstructured":"Lee, J., et al.: UniCLIP: unified framework for contrastive language-image pre-training. Adv. Neural. Inf. Process. Syst. 35, 1008\u20131019 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: An embarrassingly simple backdoor attack on self-supervised learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4367\u20134378 (2023)","DOI":"10.1109\/ICCV51070.2023.00403"},{"key":"23_CR13","unstructured":"Li, Y., et al.: Supervision exists everywhere: a data efficient contrastive language-image pre-training paradigm. arXiv preprint arXiv:2110.05208 (2021)"},{"key":"23_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"TY Lin","year":"2014","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"23_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2023.102182","volume":"146","author":"AL Opdahl","year":"2023","unstructured":"Opdahl, A.L., et al.: Trustworthy journalism through AI. Data Knowl. Eng. 146, 102182 (2023)","journal-title":"Data Knowl. Eng."},{"key":"23_CR16","unstructured":"Paszke, A.: Pytorch: an imperative style, high-performance deep learning library. arXiv preprint arXiv:1912.01703 (2019)"},{"key":"23_CR17","doi-asserted-by":"publisher","first-page":"3469","DOI":"10.1109\/TMM.2023.3311646","volume":"26","author":"F Peng","year":"2023","unstructured":"Peng, F., Yang, X., Xiao, L., Wang, Y., Xu, C.: SgVA-CLIP: semantic-guided visual adapting of vision-language models for few-shot image classification. IEEE Trans. Multimedia 26, 3469\u20133480 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"23_CR18","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International conference on machine learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Rao, Y., et al.: DenseCLIP: language-guided dense prediction with context-aware prompting. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 18082\u201318091 (2022)","DOI":"10.1109\/CVPR52688.2022.01755"},{"issue":"5","key":"23_CR20","doi-asserted-by":"publisher","first-page":"2660","DOI":"10.1109\/TCSS.2023.3268683","volume":"10","author":"L Sang","year":"2023","unstructured":"Sang, L., Xu, M., Qian, S., Wu, X.: Adversarial heterogeneous graph neural network for robust recommendation. IEEE Trans. Comput. Soc. Syst. 10(5), 2660\u20132671 (2023). https:\/\/doi.org\/10.1109\/TCSS.2023.3268683","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Shen, Y., et al.: ChatGPT and other large language models are double-edged swords (2023)","DOI":"10.1148\/radiol.230163"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Flava: a foundational language and vision alignment model. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 15638\u201315650 (2022)","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"23_CR23","doi-asserted-by":"publisher","unstructured":"Wang, Y., Xue, D., Zhang, S., Qian, S.: BadAgent: inserting and activating backdoor attacks in LLM agents. In: Ku, L.W., Martins, A., Srikumar, V. (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 9811\u20139827. Association for Computational Linguistics, Bangkok, Thailand (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.530, https:\/\/aclanthology.org\/2024.acl-long.530\/","DOI":"10.18653\/v1\/2024.acl-long.530"},{"key":"23_CR24","unstructured":"Weiser, B., Schweber, N.: Lawyer who used ChatGPT faces penalty for made up citations. The New York Times 8 (2023)"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Wu, H.H., Seetharaman, P., Kumar, K., Bello, J.P.: Wav2CLIP: learning robust audio representations from clip. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4563\u20134567. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Wang, W.Y.: On hallucination and predictive uncertainty in conditional language generation. arXiv preprint arXiv:2103.15025 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.236"},{"key":"23_CR27","unstructured":"Yang, Z., et al.: XLNet: generalized autoregressive pretraining for language understanding. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"23_CR28","unstructured":"Yang, Z., et al.: Data poisoning attacks against multimodal encoders. In: International Conference on Machine Learnin,. pp. 39299\u201339313. PMLR (2023)"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3729-7_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T16:44:00Z","timestamp":1761929040000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3729-7_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,1]]},"ISBN":["9789819537280","9789819537297"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3729-7_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,1]]},"assertion":[{"value":"1 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xuzhou","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icig.csig.org.cn\/2025\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}