{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:45:10Z","timestamp":1787017510091,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Australian Research Council Discovery Project","award":["CE200100025"],"award-info":[{"award-number":["CE200100025"]}]},{"name":"Australian Research Council Discovery Project","award":["DP230101196"],"award-info":[{"award-number":["DP230101196"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657781","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"862-871","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["Universal Adversarial Perturbations for Vision-Language Pre-trained Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6790-2098","authenticated-orcid":false,"given":"Peng-Fei","family":"Zhang","sequence":"first","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9738-4949","authenticated-orcid":false,"given":"Zi","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6390-9890","authenticated-orcid":false,"given":"Guangdong","family":"Bai","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"32","author":"Baluja Shumeet","year":"2018","unstructured":"Shumeet Baluja and Ian Fischer. 2018. Learning to attack: adversarial transfor-mation networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"e_1_3_2_1_4_1","volume-title":"Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325","author":"Chen Xinlei","year":"2015","unstructured":"Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2015. Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611823"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An image is worth 16x16 words: transformers for image recognition at scale. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_1_8_1","volume-title":"Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572","author":"Goodfellow Ian J","year":"2014","unstructured":"Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)."},{"key":"e_1_3_2_1_9_1","volume-title":"SA-Attack: improving adversarial transferability of vision-Language pretraining models via self-augmentation. arXiv preprint arXiv:2312.04913","author":"He Bangyan","year":"2023","unstructured":"Bangyan He, Xiaojun Jia, Siyuan Liang, Tianrui Lou, Yang Liu, and Xiaochun Cao. 2023. SA-Attack: improving adversarial transferability of vision-Language pretraining models via self-augmentation. arXiv preprint arXiv:2312.04913 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_11_1","volume-title":"Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533","author":"Kurakin Alexey","year":"2016","unstructured":"Alexey Kurakin, Ian J Goodfellow, and Samy Bengio. 2016. Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533 (2016)."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the International Conference on Machine Learning. PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In Proceedings of the International Conference on Machine Learning. PMLR, 12888--12900."},{"key":"e_1_3_2_1_13_1","volume-title":"Align before fuse: vision and language representation learning with momentum distillation. Advances in neural information processing systems 34","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: vision and language representation learning with momentum distillation. Advances in neural information processing systems 34 (2021), 9694--9705."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Lin Jiadong","year":"2019","unstructured":"Jiadong Lin, Chuanbiao Song, Kun He, Liwei Wang, and John E Hopcroft. 2019. Nesterov accelerated gradient and scale invariance for adversarial attacks. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Liu Yanpei","year":"2016","unstructured":"Yanpei Liu, Xinyun Chen, Chang Liu, and Dawn Song. 2016. Delving into transferable adversarial examples and black-box attacks. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00016"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Madry Aleksander","year":"2018","unstructured":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2018. Towards deep learning models resistant to adversarial attacks. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"e_1_3_2_1_21_1","volume-title":"Transferability in machine learning: from phenomena to black-box attacks using adversarial samples. arXiv preprint arXiv:1605.07277","author":"Papernot Nicolas","year":"2016","unstructured":"Nicolas Papernot, Patrick McDaniel, and Ian Goodfellow. 2016. Transferability in machine learning: from phenomena to black-box attacks using adversarial samples. arXiv preprint arXiv:1605.07277 (2016)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00465"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the International Conference on Machine Learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In Proceedings of the International Conference on Machine Learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_26_1","volume-title":"Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199","author":"Szegedy Christian","year":"2013","unstructured":"Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2013. Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Szegedy Christian","year":"2014","unstructured":"Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2014. Intriguing properties of neural networks. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01585"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Wang Xin","year":"2020","unstructured":"Xin Wang, Jie Ren, Shuyun Lin, Xiangming Zhu, Yisen Wang, and Quanshi Zhang. 2020. A unified approach to interpreting and boosting adversarial transferability. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_1_30_1","volume-title":"Exploring transferability of multimodal adversarial samples for vision-language pre-training models with contrastive learning. arXiv preprint arXiv:2308.12636","author":"Wang Youze","year":"2023","unstructured":"Youze Wang, Wenbo Hu, Yinpeng Dong, and Richang Hong. 2023. Exploring transferability of multimodal adversarial samples for vision-language pre-training models with contrastive learning. arXiv preprint arXiv:2308.12636 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00284"},{"key":"e_1_3_2_1_32_1","volume-title":"Visual entailment: a novel task for fine-grained image understanding. arXiv preprint arXiv:1901.06706","author":"Xie Ning","year":"2019","unstructured":"Ning Xie, Farley Lai, Derek Doran, and Asim Kadav. 2019. Visual entailment: a novel task for fine-grained image understanding. arXiv preprint arXiv:1901.06706 (2019)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547801"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3545799"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16449"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3053766"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462837"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-020-00859-y"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612454"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657781","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657781","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:40:57Z","timestamp":1755841257000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657781"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":42,"alternative-id":["10.1145\/3626772.3657781","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657781","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}