{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T11:10:06Z","timestamp":1789125006060,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372802","type":"print"},{"value":"9783032372819","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\/978-3-032-37281-9_7","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:51:32Z","timestamp":1789123892000},"page":"115-132","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Are GUI Agents Focused Enough? Automated Distraction via\u00a0Semantic-Level UI Element Injection"],"prefix":"10.1007","author":[{"given":"Wenkui","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haisu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weilin","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Derek","family":"Yuen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junxian","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaibo","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ran","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"7_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1007\/978-3-030-58592-1_29","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Andriushchenko","year":"2020","unstructured":"Andriushchenko, M., Croce, F., Flammarion, N., Hein, M.: Square attack: a query-efficient black-box adversarial attack via random search. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 484\u2013501. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_29"},{"key":"7_CR2","unstructured":"Anthropic: Claude sonnet 4.6 system card (2026). https:\/\/anthropic.com\/claude-sonnet-4-6-system-card. Accessed 17 Feb 2026"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Bai, C., Zang, X., Xu, Y., Sunkara, S., Rastogi, A., Chen, J.: UIBert: learning generic multimodal representations for UI understanding. In: International Joint Conferences on Artificial Intelligence (2021)","DOI":"10.24963\/ijcai.2021\/235"},{"key":"7_CR4","unstructured":"Bai, S., et al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"7_CR5","unstructured":"ByteDance Seed Team: Seed2.0 Pro (2026). https:\/\/seed.bytedance.com\/en\/seed2, seed2.0 series model page. Accessed 01 July 2026"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Chai, Y., et al.: AMEX: android multi-annotation expo dataset for mobile GUI agents. In: Annual Meeting of the Association for Computational Linguistics, pp. 2138\u20132156 (2025)","DOI":"10.18653\/v1\/2025.findings-acl.110"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Chao, P., Robey, A., Dobriban, E., Hassani, H., Pappas, G.J., Wong, E.: Jailbreaking black box large language models in twenty queries. In: 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), pp. 23\u201342. IEEE (2025)","DOI":"10.1109\/SaTML64287.2025.00010"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Chen, G., et al.: Less is more: empowering GUI agent with context-aware simplification. In: IEEE\/CVF International Conference on Computer Vision, pp. 5901\u20135911 (2025)","DOI":"10.1109\/ICCV51701.2025.00558"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Can indirect prompt injection attacks be detected and removed? In: Annual Meeting of the Association for Computational Linguistics, pp. 18189\u201318206 (2025)","DOI":"10.18653\/v1\/2025.acl-long.890"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Y., Li, H., Zheng, Z., Wu, D., Song, Y., Hooi, B.: Defense against prompt injection attack by leveraging attack techniques. In: Annual Meeting of the Association for Computational Linguistics, pp. 18331\u201318347 (2025)","DOI":"10.18653\/v1\/2025.acl-long.897"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, K., et al.: Seeclick: harnessing GUI grounding for advanced visual GUI agents. In: Annual Meeting of the Association for Computational Linguistics, pp. 9313\u20139332 (2024)","DOI":"10.18653\/v1\/2024.acl-long.505"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Croce, F., Andriushchenko, M., Singh, N.D., Flammarion, N., Hein, M.: Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 6437\u20136445 (2022)","DOI":"10.1609\/aaai.v36i6.20595"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Deka, B., et al.: Rico: a mobile app dataset for building data-driven design applications. In: Proceedings of the 30th Annual ACM Symposium on User Interface Software and Technology, pp. 845\u2013854 (2017)","DOI":"10.1145\/3126594.3126651"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Douze, M., et al.: The faiss library. IEEE Trans. Big Data (2025)","DOI":"10.1109\/TBDATA.2025.3618474"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Evtimov, I., Zharmagambetov, A., Grattafiori, A., Guo, C., Chaudhuri, K.: Wasp: benchmarking web agent security against prompt injection attacks. In: Advances in Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-0666"},{"key":"7_CR16","unstructured":"Gao, C., et al.: Ui-venus-1.5 technical report. arXiv preprint arXiv:2602.09082 (2026)"},{"key":"7_CR17","unstructured":"Google DeepMind: Model evaluation \u2013 approach, methodology & results: Gemini 3 flash (2025). https:\/\/storage.googleapis.com\/deepmind-media\/gemini\/gemini_3_flash_model_evaluation.pdf, model id: gemini-3-flash-preview"},{"key":"7_CR18","unstructured":"Gu, Z., et al.: Ui-venus technical report: building high-performance UI agents with RFT. arXiv preprint arXiv:2508.10833 (2025)"},{"key":"7_CR19","unstructured":"Koh, W., Han, S., Lee, S., Yun, S.Y., Shin, J.: Generative visual code mobile world models. In: Proceedings of the International Conference on Machine Learning (2026)"},{"key":"7_CR20","unstructured":"Li, G., Li, Y.: Spotlight: mobile UI understanding using vision-language models with a focus. In: Proceedings of the International Conference on Learning Representations (2023)"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Li, H., Liu, X., Zhang, N., Xiao, C.: Piguard: prompt injection guardrail via mitigating overdefense for free. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 30420\u201330437 (2025)","DOI":"10.18653\/v1\/2025.acl-long.1468"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: Screenspot-Pro: GUI grounding for professional high-resolution computer use. In: Proceedings of the ACM International Conference on Multimedia, pp. 8778\u20138786 (2025)","DOI":"10.1145\/3746027.3755688"},{"key":"7_CR23","unstructured":"Li, M., et\u00a0al.: Qwen3-VL-embedding and qwen3-VL-reranker: a unified framework for state-of-the-art multimodal retrieval and ranking. arXiv preprint arXiv:2601.04720 (2026)"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Lin, K.Q., et al.: Showui: one vision-language-action model for GUI visual agent. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19498\u201319508 (2025)","DOI":"10.1109\/CVPR52734.2025.01816"},{"key":"7_CR25","unstructured":"Liu, Y., et al.: InfiGUI-R1: advancing multimodal GUI agents from reactive actors to deliberative reasoners. arXiv preprint arXiv:2504.14239 (2025)"},{"key":"7_CR26","unstructured":"Lu, Y., Yang, J., Shen, Y., Awadallah, A.: Omniparser for pure vision based GUI agent. arXiv preprint arXiv:2408.00203 (2024)"},{"key":"7_CR27","unstructured":"Luo, D., et al.: Vimo: a generative visual GUI world model for app agents. In: Proceedings of the International Conference on Learning Representations (2026)"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Mehrotra, A., et al.: Tree of attacks: jailbreaking black-box LLMs automatically. In: Advances in Neural Information Processing Systems, vol. 37, pp. 61065\u201361105 (2024)","DOI":"10.52202\/079017-1952"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Qi, X., Huang, K., Panda, A., Henderson, P., Wang, M., Mittal, P.: Visual adversarial examples jailbreak aligned large language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 21527\u201321536 (2024)","DOI":"10.1609\/aaai.v38i19.30150"},{"key":"7_CR30","unstructured":"Qi, X., et al.: Safety alignment should be made more than just a few tokens deep. In: Proceedings of the International Conference on Learning Representations (2025)"},{"key":"7_CR31","unstructured":"Qi, X., et al.: Fine-tuning aligned language models compromises safety, even when users do not intend to! In: Proceedings of the International Conference on Learning Representations (2024)"},{"key":"7_CR32","unstructured":"Qin, Y., et al.: UI-tars: pioneering automated GUI interaction with native agents. arXiv preprint arXiv:2501.12326 (2025)"},{"key":"7_CR33","unstructured":"Qwen Team: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"7_CR34","unstructured":"Rawles, C., et\u00a0al.: Androidworld: a dynamic benchmarking environment for autonomous agents. In: Proceedings of the International Conference on Learning Representations (2025)"},{"key":"7_CR35","unstructured":"Wang, H., et\u00a0al.: UI-tars-2 technical report: advancing GUI agent with multi-turn reinforcement learning. arXiv preprint arXiv:2509.02544 (2025)"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: OpenCUA: open foundations for computer-use agents. In: Advances in Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-4669"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Y., Guan, J., Liang, J., He, R.: Do we really need curated malicious data for safety alignment in multi-modal large language models? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19879\u201319889 (2025)","DOI":"10.1109\/CVPR52734.2025.01851"},{"key":"7_CR38","unstructured":"Wang, Y., Yu, Y., Liang, J., He, R.: A comprehensive survey on trustworthiness in reasoning with large language models. arXiv preprint arXiv:2509.03871 (2025)"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Wu, Q., et al.: GUI-actor: coordinate-free visual grounding for GUI agents. In: Advances in Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-0508"},{"key":"7_CR40","unstructured":"Wu, Z., et al.: OS-ATLAS: a foundation action model for generalist GUI agents. In: Proceedings of the International Conference on Learning Representations (2025)"},{"key":"7_CR41","doi-asserted-by":"crossref","unstructured":"Xie, P., et al.: Chain of attack: on the robustness of vision-language models against transfer-based adversarial attacks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14679\u201314689 (2025)","DOI":"10.1109\/CVPR52734.2025.01368"},{"key":"7_CR42","unstructured":"Xu, H., et al.: Mobile-agent-v3. 5: multi-platform fundamental GUI agents. arXiv preprint arXiv:2602.16855 (2026)"},{"key":"7_CR43","unstructured":"Xu, Y., et al.: Aguvis: unified pure vision agents for autonomous GUI interaction. In: International Conference on Machine Learning (2025)"},{"key":"7_CR44","unstructured":"Xue, T., et\u00a0al.: EvoCUA: evolving computer use agents via learning from scalable synthetic experience. arXiv preprint arXiv:2601.15876 (2026)"},{"key":"7_CR45","unstructured":"Ye, J., et al.: Mobile-agent-v3: fundamental agents for GUI automation. arXiv preprint arXiv:2508.15144 (2025)"},{"key":"7_CR46","unstructured":"Yu, J., Lin, X., Yu, Z., Xing, X.: GPTFUZZER: red teaming large language models with auto-generated jailbreak prompts. arXiv preprint arXiv:2309.10253 (2023)"},{"key":"7_CR47","unstructured":"Yu, J., Lin, X., Yu, Z., Xing, X.: $$\\{$$LLM-Fuzzer$$\\}$$: scaling assessment of large language model jailbreaks. In: Proceedings of the USENIX Conference on Security Symposium, pp. 4657\u20134674 (2024)"},{"key":"7_CR48","unstructured":"Yu, Y., et al.: Reassessing the role of supervised fine-tuning: an empirical study in VLM reasoning. arXiv preprint arXiv:2512.12690 (2025)"},{"key":"7_CR49","unstructured":"Yu, Y., Wang, Y., He, R., Liang, J.: Test-time immunization: a universal defense framework against jailbreaks for (multimodal) large language models. arXiv preprint arXiv:2505.22271 (2025)"},{"key":"7_CR50","doi-asserted-by":"crossref","unstructured":"Yuan, X., et al.: Se-GUI: enhancing visual grounding for GUI agents via self-evolutionary reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 38, pp. 127658\u2013127679 (2025)","DOI":"10.52202\/085713-4251"},{"key":"7_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Anyattack: towards large-scale self-supervised adversarial attacks on vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19900\u201319909 (2025)","DOI":"10.1109\/CVPR52734.2025.01853"},{"key":"7_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: AgentCPM-GUI: building mobile-use agents with reinforcement fine-tuning. In: EMNLP (2025)","DOI":"10.18653\/v1\/2025.emnlp-demos.12"},{"key":"7_CR53","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: On evaluating adversarial robustness of large vision-language models. In: Advances in Neural Information Processing Systems, vol. 36, pp. 54111\u201354138 (2023)","DOI":"10.52202\/075280-2355"},{"key":"7_CR54","doi-asserted-by":"crossref","unstructured":"Zharmagambetov, A., Guo, C., Evtimov, I., Pavlova, M., Salakhutdinov, R., Chaudhuri, K.: AgentDAM: privacy leakage evaluation for autonomous web agents. In: Advances in Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-4609"},{"key":"7_CR55","unstructured":"Zheng, B., Gou, B., Kil, J., Sun, H., Su, Y.: GPT-4V (ision) is a generalist web agent, if grounded. In: Proceedings of the International Conference on Machine Learning (2024)"},{"key":"7_CR56","unstructured":"Zheng, Y., et al.: Code2world: a GUI world model via renderable code generation. arXiv preprint arXiv:2602.09856 (2026)"},{"key":"7_CR57","unstructured":"Zhu, K., Yang, X., Wang, J., Guo, W., Wang, W.Y.: MELON: provable defense against indirect prompt injection attacks in AI agents. In: International Conference on Machine Learning (2025)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37281-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:51:47Z","timestamp":1789123907000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37281-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372802","9783032372819"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37281-9_7","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":"12 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}