{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:30:48Z","timestamp":1776889848146,"version":"3.51.2"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031736490","type":"print"},{"value":"9783031736506","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73650-6_27","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T18:18:06Z","timestamp":1732126686000},"page":"467-483","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["TrojVLM: Backdoor Attack Against Vision Language Models"],"prefix":"10.1007","author":[{"given":"Weimin","family":"Lyu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Pang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tengfei","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haibin","family":"Ling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"27_CR1","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"27_CR3","unstructured":"Banerjee, S., Lavie, A.: Meteor: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"27_CR4","unstructured":"Carlini, N., Terzis, A.: Poisoning and backdooring contrastive learning. arXiv preprint arXiv:2106.09667 (2021)"},{"key":"27_CR5","unstructured":"Chen, X., Liu, C., Li, B., Lu, K., Song, D.: Targeted backdoor attacks on deep learning systems using data poisoning. arXiv preprint arXiv:1712.05526 (2017)"},{"key":"27_CR6","unstructured":"Chin-Yew, L.: Rouge: A package for automatic evaluation of summaries. In: Proceedings of the Workshop on Text Summarization Branches Out, 2004 (2004)"},{"key":"27_CR7","first-page":"5009","volume":"35","author":"G Cui","year":"2022","unstructured":"Cui, G., Yuan, L., He, B., Chen, Y., Liu, Z., Sun, M.: A unified evaluation of textual backdoor learning: Frameworks and benchmarks. Adv. Neural. Inf. Process. Syst. 35, 5009\u20135023 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR8","unstructured":"Dai, W., et al.: Instructblip: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the v in VQA matter: elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"27_CR10","unstructured":"Gu, T., Dolan-Gavitt, B., BadNets, S.: Identifying vulnerabilities in the machine learning model supply chain. In: Proceedings of the Neural Information Processing Symposium Workshop Mach. Learning Security (MLSec), pp.\u00a01\u20135 (2017)"},{"key":"27_CR11","unstructured":"Han, X., et al.: Backdooring multimodal learning. In: 2024 IEEE Symposium on Security and Privacy (SP), pp. 31\u201331. IEEE Computer Society (2023)"},{"key":"27_CR12","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh, M., Young, P., Hockenmaier, J.: Framing image description as a ranking task: data, models and evaluation metrics. J. Artif. Intell. Res. 47, 853\u2013899 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"27_CR13","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":"27_CR14","doi-asserted-by":"publisher","first-page":"1525052","DOI":"10.1155\/2022\/1525052","volume":"2022","author":"H Kwon","year":"2022","unstructured":"Kwon, H., Lee, S.: Toward backdoor attacks for image captioning model in deep neural networks. Secur. Commun. Netw. 2022, 1525052 (2022)","journal-title":"Secur. Commun. Netw."},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Li, D., Li, J., Le, H., Wang, G., Savarese, S., Hoi, S.C.: LAVIS: a one-stop library for language-vision intelligence. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pp. 31\u201341. Association for Computational Linguistics, Toronto, Canada, July 2023. https:\/\/aclanthology.org\/2023.acl-demo.3","DOI":"10.18653\/v1\/2023.acl-demo.3"},{"key":"27_CR16","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"27_CR17","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Li, M., Zhong, N., Zhang, X., Qian, Z., Li, S.: Object-oriented backdoor attack against image captioning. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2864\u20132868. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746440"},{"issue":"1","key":"27_CR19","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1109\/TNNLS.2022.3182979","volume":"35","author":"Y Li","year":"2022","unstructured":"Li, Y., Jiang, Y., Li, Z., Xia, S.T.: Backdoor learning: a survey. IEEE Trans. Neural Netw. Learn. Syst. 35(1), 5\u201322 (2022)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"27_CR20","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":"T-Y 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":"27_CR21","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"27_CR22","unstructured":"Lu, D., Pang, T., Du, C., Liu, Q., Yang, X., Lin, M.: Test-time backdoor attacks on multimodal large language models. arXiv preprint arXiv:2402.08577 (2024)"},{"key":"27_CR23","unstructured":"Lyu, W., Zheng, S., Ling, H., Chen, C.: Backdoor attacks against transformers with attention enhancement. In: ICLR 2023 Workshop on Backdoor Attacks and Defenses in Machine Learning (2023)"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Lyu, W., Zheng, S., Ma, T., Chen, C.: A study of the attention abnormality in trojaned berts. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4727\u20134741 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.348"},{"key":"27_CR25","unstructured":"Lyu, W., Zheng, S., Ma, T., Ling, H., Chen, C.: Attention hijacking in trojan transformers. arXiv preprint arXiv:2208.04946 (2022)"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Lyu, W., Zheng, S., Pang, L., Ling, H., Chen, C.: Attention-enhancing backdoor attacks against bert-based models. In: Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 10672\u201310690 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.716"},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: Ok-vqa: a visual question answering benchmark requiring external knowledge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3195\u20133204 (2019)","DOI":"10.1109\/CVPR.2019.00331"},{"key":"27_CR28","unstructured":"OpenAI: Gpt-4v(ision) system card. https:\/\/cdn.openai.com\/papers\/GPTV_System_Card.pdf (2023)"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"27_CR30","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"8","key":"27_CR31","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"27_CR33","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Walmer, M., Sikka, K., Sur, I., Shrivastava, A., Jha, S.: Dual-key multimodal backdoors for visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15375\u201315385 (2022)","DOI":"10.1109\/CVPR52688.2022.01494"},{"key":"27_CR35","unstructured":"Xu, Y., et al.: Shadowcast: stealthy data poisoning attacks against vision-language models. arXiv preprint arXiv:2402.06659 (2024)"},{"key":"27_CR36","unstructured":"Yang, Z., et al.: Data poisoning attacks against multimodal encoders. In: International Conference on Machine Learning, pp. 39299\u201339313. PMLR (2023)"},{"key":"27_CR37","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"27_CR38","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73650-6_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T19:07:56Z","timestamp":1732129676000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73650-6_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031736490","9783031736506"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73650-6_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}