{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:15:09Z","timestamp":1783152909281,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62472302"],"award-info":[{"award-number":["62472302"]}]},{"name":"Key Research and Development Program of Shanxi Province","award":["202402150101007"],"award-info":[{"award-number":["202402150101007"]}]},{"name":"Open Project of the State Key Laboratory of Internet Architecture","award":["HLW2025MS31"],"award-info":[{"award-number":["HLW2025MS31"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792315","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:39Z","timestamp":1775771679000},"page":"2824-2834","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Breaking Cross-modal Alignment in Embodied Intelligence: A Multimodal Adversarial Attack Framework for Vision-Language-Action Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0695-1199","authenticated-orcid":false,"given":"Zhihui","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan, Shanxi, China and State Key Laboratory of Internet Architecture, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1337-1678","authenticated-orcid":false,"given":"Xiaorong","family":"Dong","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Industrial Internet Security, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8953-0782","authenticated-orcid":false,"given":"Yaowen","family":"Zheng","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3921-7907","authenticated-orcid":false,"given":"Xiaohui","family":"Chen","sequence":"additional","affiliation":[{"name":"China Mobile Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7543-0326","authenticated-orcid":false,"given":"Yimo","family":"Ren","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7310-7636","authenticated-orcid":false,"given":"Hangbei","family":"Cheng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1000-1109","authenticated-orcid":false,"given":"Yongle","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Taiyuan University of Technology, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Industrial Internet Security, Taiyuan, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2745-7521","authenticated-orcid":false,"given":"Limin","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00395"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.7753\/IJSEA0207.1002"},{"key":"e_1_3_2_1_3_1","volume-title":"Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion. arXiv preprint arXiv:2505.14316","author":"Cui Tiehan","year":"2025","unstructured":"Tiehan Cui, Yanxu Mao, Peipei Liu, Congying Liu, and Datao You. 2025. Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion. arXiv preprint arXiv:2505.14316 (2025)."},{"key":"e_1_3_2_1_4_1","volume-title":"Fast Fourier transforms: a tutorial review and a state of the art. Signal processing","author":"Duhamel Pierre","year":"1990","unstructured":"Pierre Duhamel and Martin Vetterli. 1990. Fast Fourier transforms: a tutorial review and a state of the art. Signal processing, Vol. 19, 4 (1990), 259-299."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-024-01603-z"},{"key":"e_1_3_2_1_6_1","volume-title":"Vision-language navigation with embodied intelligence: A survey. arXiv preprint arXiv:2402.14304","author":"Gao Peng","year":"2024","unstructured":"Peng Gao, Peng Wang, Feng Gao, Fei Wang, and Ruyue Yuan. 2024. Vision-language navigation with embodied intelligence: A survey. arXiv preprint arXiv:2402.14304 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"R-LPIPS: An adversarially robust perceptual similarity metric. arXiv preprint arXiv:2307.15157","author":"Ghazanfari Sara","year":"2023","unstructured":"Sara Ghazanfari, Siddharth Garg, Prashanth Krishnamurthy, Farshad Khorrami, and Alexandre Araujo. 2023. R-LPIPS: An adversarially robust perceptual similarity metric. arXiv preprint arXiv:2307.15157 (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1029\/2021MS002681"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/sym17030462"},{"key":"e_1_3_2_1_10_1","volume-title":"Doubly-universal adversarial perturbations: Deceiving vision-language models across both images and text with a single perturbation. arXiv preprint arXiv:2412.08108","author":"Kim Hee-Seon","year":"2024","unstructured":"Hee-Seon Kim, Minbeom Kim, and Changick Kim. 2024a. Doubly-universal adversarial perturbations: Deceiving vision-language models across both images and text with a single perturbation. arXiv preprint arXiv:2412.08108 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"Fine-tuning vision-language-action models: Optimizing speed and success. arXiv preprint arXiv:2502.19645","author":"Kim Moo Jin","year":"2025","unstructured":"Moo Jin Kim, Chelsea Finn, and Percy Liang. 2025. Fine-tuning vision-language-action models: Optimizing speed and success. arXiv preprint arXiv:2502.19645 (2025)."},{"key":"e_1_3_2_1_12_1","volume-title":"Openvla: An open-source vision-language-action model. arXiv preprint arXiv:2406.09246","author":"Kim Moo Jin","year":"2024","unstructured":"Moo Jin Kim, Karl Pertsch, Siddharth Karamcheti, Ted Xiao, Ashwin Balakrishna, Suraj Nair, Rafael Rafailov, Ethan Foster, Grace Lam, Pannag Sanketi, et al., 2024b. Openvla: An open-source vision-language-action model. arXiv preprint arXiv:2406.09246 (2024)."},{"key":"e_1_3_2_1_13_1","volume-title":"CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification. arXiv preprint arXiv:2508.21046","author":"Li Wei","year":"2025","unstructured":"Wei Li, Renshan Zhang, Rui Shao, Jie He, and Liqiang Nie. 2025. CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification. arXiv preprint arXiv:2508.21046 (2025)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004802"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1939"},{"key":"e_1_3_2_1_17_1","volume-title":"PlAA: Pixel-level Adversarial Attack on Attention for Deep Neural Network. In International Conference on Artificial Neural Networks. Springer, 611-623","author":"Liu Huailin","year":"2022","unstructured":"Huailin Liu and Jing Liu. 2022. PlAA: Pixel-level Adversarial Attack on Attention for Deep Neural Network. In International Conference on Artificial Neural Networks. Springer, 611-623."},{"key":"e_1_3_2_1_18_1","volume-title":"From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem. arXiv preprint arXiv:2506.15170","author":"Mao Yanxu","year":"2025","unstructured":"Yanxu Mao, Tiehan Cui, Peipei Liu, Datao You, and Hongsong Zhu. 2025. From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem. arXiv preprint arXiv:2506.15170 (2025)."},{"key":"e_1_3_2_1_19_1","volume-title":"Divide and conquer: A hybrid strategy defeats multimodal large language models. arXiv preprint arXiv:2412.16555","author":"Mao Yanxu","year":"2024","unstructured":"Yanxu Mao, Peipei Liu, Tiehan Cui, Zhaoteng Yan, Congying Liu, and Datao You. 2024. Divide and conquer: A hybrid strategy defeats multimodal large language models. arXiv preprint arXiv:2412.16555 (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00143"},{"key":"e_1_3_2_1_21_1","volume-title":"Spatialvla: Exploring spatial representations for visual-language-action model. arXiv preprint arXiv:2501.15830","author":"Qu Delin","year":"2025","unstructured":"Delin Qu, Haoming Song, Qizhi Chen, Yuanqi Yao, Xinyi Ye, Yan Ding, Zhigang Wang, JiaYuan Gu, Bin Zhao, Dong Wang, et al., 2025. Spatialvla: Exploring spatial representations for visual-language-action model. arXiv preprint arXiv:2501.15830 (2025)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_23_1","volume-title":"Low-rank adversarial pgd attack. arXiv preprint arXiv:2410.12607","author":"Savostianova Dayana","year":"2024","unstructured":"Dayana Savostianova, Emanuele Zangrando, and Francesco Tudisco. 2024. Low-rank adversarial pgd attack. arXiv preprint arXiv:2410.12607 (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"2020 IEEE International Conference on Image Processing (ICIP). IEEE, 718-722","author":"Ali Shah Syed Afaq","year":"2020","unstructured":"Syed Afaq Ali Shah, Moise Beugre, Naveed Akhtar, Mohammed Bennamoun, and Liang Zhang. 2020. Efficient detection of pixel-level adversarial attacks. In 2020 IEEE International Conference on Image Processing (ICIP). IEEE, 718-722."},{"key":"e_1_3_2_1_25_1","volume-title":"Smolvla: A vision-language-action model for affordable and efficient robotics. arXiv preprint arXiv:2506.01844","author":"Shukor Mustafa","year":"2025","unstructured":"Mustafa Shukor, Dana Aubakirova, Francesco Capuano, Pepijn Kooijmans, Steven Palma, Adil Zouitine, Michel Aractingi, Caroline Pascal, Martino Russi, Andres Marafioti, et al., 2025. Smolvla: A vision-language-action model for affordable and efficient robotics. arXiv preprint arXiv:2506.01844 (2025)."},{"key":"e_1_3_2_1_26_1","volume-title":"CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding. arXiv preprint arXiv:2506.13725","author":"Song Wenxuan","year":"2025","unstructured":"Wenxuan Song, Jiayi Chen, Pengxiang Ding, Yuxin Huang, Han Zhao, Donglin Wang, and Haoang Li. 2025. CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding. arXiv preprint arXiv:2506.13725 (2025)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3238397"},{"key":"e_1_3_2_1_28_1","volume-title":"Wenhao Yang, Dongfang Liu, Luna Xinyu Zhang, Qifan Wang, Jiebo Luo, and Ruixiang Tang.","author":"Wang Taowen","year":"2024","unstructured":"Taowen Wang, Cheng Han, James Chenhao Liang, Wenhao Yang, Dongfang Liu, Luna Xinyu Zhang, Qifan Wang, Jiebo Luo, and Ruixiang Tang. 2024. Exploring the adversarial vulnerabilities of vision-language-action models in robotics. arXiv preprint arXiv:2411.13587 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"ADVEDM: Fine-grained Adversarial Attack against VLM-based Embodied Agents. arXiv preprint arXiv:2509.16645","author":"Wang Yichen","year":"2025","unstructured":"Yichen Wang, Hangtao Zhang, Hewen Pan, Ziqi Zhou, Xianlong Wang, Peijin Guo, Lulu Xue, Shengshan Hu, Minghui Li, and Leo Yu Zhang. 2025. ADVEDM: Fine-grained Adversarial Attack against VLM-based Embodied Agents. arXiv preprint arXiv:2509.16645 (2025)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIEA58696.2023.10241832"},{"key":"e_1_3_2_1_31_1","volume-title":"Adversarial attacks of vision tasks in the past 10 years: A survey. Comput. Surveys","author":"Zhang Chiyu","year":"2024","unstructured":"Chiyu Zhang, Lu Zhou, Xiaogang Xu, Jiafei Wu, and Zhe Liu. 2024c. Adversarial attacks of vision tasks in the past 10 years: A survey. Comput. Surveys (2024)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_1_33_1","volume-title":"Visual adversarial attack on vision-language models for autonomous driving. arXiv preprint arXiv:2411.18275","author":"Zhang Tianyuan","year":"2024","unstructured":"Tianyuan Zhang, Lu Wang, Xinwei Zhang, Yitong Zhang, Boyi Jia, Siyuan Liang, Shengshan Hu, Qiang Fu, Aishan Liu, and Xianglong Liu. 2024b. Visual adversarial attack on vision-language models for autonomous driving. arXiv preprint arXiv:2411.18275 (2024)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612454"},{"key":"e_1_3_2_1_35_1","volume-title":"Nima Tajbakhsh, and Jianming Liang.","author":"Zhou Zongwei","year":"2019","unstructured":"Zongwei Zhou, Md Mahfuzur Rahman Siddiquee, Nima Tajbakhsh, and Jianming Liang. 2019. Unet: Redesigning skip connections to exploit multiscale features in image segmentation. IEEE transactions on medical imaging, Vol. 39, 6 (2019), 1856-1867."}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:16:39Z","timestamp":1783149399000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792315"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":35,"alternative-id":["10.1145\/3774904.3792315","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792315","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}