{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T05:01:01Z","timestamp":1770699661987,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569564","type":"print"},{"value":"9789819569571","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-981-95-6957-1_2","type":"book-chapter","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T10:44:03Z","timestamp":1770633843000},"page":"16-30","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DiSCo: Disrupting Semantic Consistency for\u00a0Transferable Cross-Modal Adversarial Attacks"],"prefix":"10.1007","author":[{"given":"Peirou","family":"Liang","sequence":"first","affiliation":[]},{"given":"Meng","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Zhiqian","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Peng Yuan","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Liao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,10]]},"reference":[{"key":"2_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":"2_CR2","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 397\u2013406 (2021)","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"2_CR3","doi-asserted-by":"publisher","unstructured":"Cheng, H., et al.: Unveiling typographic deceptions: insights of the typographic vulnerability in large vision-language models. In: European Conference on Computer Vision, pp. 179\u2013196. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73202-7_11","DOI":"10.1007\/978-3-031-73202-7_11"},{"key":"2_CR4","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"2_CR5","doi-asserted-by":"publisher","unstructured":"Gao, S., Jia, X., Ren, X., Tsang, I., Guo, Q.: Boosting transferability in vision-language attacks via diversification along the intersection region of adversarial trajectory. In: European Conference on Computer Vision, pp. 442\u2013460. Springer,Cham. (2024). https:\/\/doi.org\/10.1007\/978-3-031-72998-0_25","DOI":"10.1007\/978-3-031-72998-0_25"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: Texture re-scalable universal adversarial perturbation. IEEE Trans. Inf. Forensics Secur. (2024)","DOI":"10.1109\/TIFS.2024.3416030"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Inkawhich, N., Wen, W., Li, H.H., Chen, Y.: Feature space perturbations yield more transferable adversarial examples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7066\u20137074 (2019)","DOI":"10.1109\/CVPR.2019.00723"},{"key":"2_CR8","unstructured":"Jia, X., et al.: Semantic-aligned adversarial evolution triangle for high-transferability vision-language attack. arXiv preprint arXiv:2411.02669 (2024)"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Khan, Z., Fu, Y.: Exploiting BERT for multimodal target sentiment classification through input space translation. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3034\u20133042 (2021)","DOI":"10.1145\/3474085.3475692"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Kim, G., Kim, J., Lee, J.S.: Exploring adversarial robustness of vision transformers in the spectral perspective. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3976\u20133985 (2024)","DOI":"10.1109\/WACV57701.2024.00393"},{"key":"2_CR11","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"2_CR12","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. Adv. Neural. Inf. Process. Syst. 34, 9694\u20139705 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Li, L., Ma, R., Guo, Q., Xue, X., Qiu, X.: BERT-ATTACK: adversarial attack against BERT using BERT. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6193\u20136202 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.500"},{"key":"2_CR14","first-page":"17612","volume":"35","author":"VW Liang","year":"2022","unstructured":"Liang, V.W., Zhang, Y., Kwon, Y., Yeung, S., Zou, J.Y.: Mind the gap: understanding the modality gap in multi-modal contrastive representation learning. Adv. Neural. Inf. Process. Syst. 35, 17612\u201317625 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Lin, J., Yin, H., Ping, W., Molchanov, P., Shoeybi, M., Han, S.: VILA: on pre-training for visual language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26689\u201326699 (2024)","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"2_CR16","doi-asserted-by":"publisher","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","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Lu, D., Wang, Z., Wang, T., Guan, W., Gao, H., Zheng, F.: Set-level guidance attack: boosting adversarial transferability of vision-language pre-training models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 102\u2013111 (2023)","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"2_CR18","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"2_CR20","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Transferable multimodal attack on vision-language pre-training models. In: 2024 IEEE Symposium on Security and Privacy (SP), pp. 1722\u20131740. IEEE (2024)","DOI":"10.1109\/SP54263.2024.00102"},{"key":"2_CR22","first-page":"121475","volume":"37","author":"W Wang","year":"2024","unstructured":"Wang, W., et al.: CogVLM: visual expert for pretrained language models. Adv. Neural. Inf. Process. Syst. 37, 121475\u2013121499 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR23","first-page":"61501","volume":"36","author":"W Wang","year":"2023","unstructured":"Wang, W., et al.: VisionLLM: large language model is also an open-ended decoder for vision-centric tasks. Adv. Neural. Inf. Process. Syst. 36, 61501\u201361513 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Wu, W.,et al.: Boosting the transferability of adversarial samples via attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1161\u20131170 (2020)","DOI":"10.1109\/CVPR42600.2020.00124"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Xu, W., Chen, K., Gao, Z., Wei, Z., Chen, J., Jiang, Y.G.: Highly transferable diffusion-based unrestricted adversarial attack on pre-trained vision-language models. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 748\u2013757 (2024)","DOI":"10.1145\/3664647.3681538"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Yang, J.,et al.: Vision-language pre-training with triple contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15671\u201315680 (2022)","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, J., Yi, Q., Sang, J.: Towards adversarial attack on vision-language pre-training models. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5005\u20135013 (2022)","DOI":"10.1145\/3503161.3547801"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Wu, J., Wang, H., He, J.: Adversarial robustness through bias variance decomposition: a new perspective for federated learning. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pp. 2753\u20132762 (2022)","DOI":"10.1145\/3511808.3557232"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Hu, S., Li, M., Zhang, H., Zhang, Y., Jin, H.: AdvCLIP: downstream-agnostic adversarial examples in multimodal contrastive learning. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 6311\u20136320 (2023)","DOI":"10.1145\/3581783.3612454"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6957-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T10:44:07Z","timestamp":1770633847000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6957-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569564","9789819569571"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6957-1_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","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":"29 January 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2026.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}