{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T15:55:25Z","timestamp":1783007725957,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755643","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:55Z","timestamp":1761377215000},"page":"4875-4883","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7541-4193","authenticated-orcid":false,"given":"Feiran","family":"Liu","sequence":"first","affiliation":[{"name":"Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1492-8800","authenticated-orcid":false,"given":"Yuzhe","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7357-5364","authenticated-orcid":false,"given":"Xinyi","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1739-9839","authenticated-orcid":false,"given":"Yinan","family":"Peng","sequence":"additional","affiliation":[{"name":"Hengxin Tech., Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9686-4369","authenticated-orcid":false,"given":"Xinfeng","family":"Li","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2518-4160","authenticated-orcid":false,"given":"Lixu","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwestern University, Evanston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1259-5856","authenticated-orcid":false,"given":"Yutong","family":"Shen","sequence":"additional","affiliation":[{"name":"Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2261-4268","authenticated-orcid":false,"given":"Ranjie","family":"Duan","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3286-6824","authenticated-orcid":false,"given":"Simeng","family":"Qin","sequence":"additional","affiliation":[{"name":"Northeast University at Qinhuangdao, Qinhuangdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2018-9344","authenticated-orcid":false,"given":"Xiaojun","family":"Jia","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4516-2524","authenticated-orcid":false,"given":"Qingsong","family":"Wen","sequence":"additional","affiliation":[{"name":"Squirrel Ai Learning, Bellevue, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0394-4125","authenticated-orcid":false,"given":"Wei","family":"Dong","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Savitha Sam Abraham Sowmya S Sundaram et al. 2019. Fairness in clustering with multiple sensitive attributes. arXiv preprint arXiv:1910.05113 (2019)."},{"key":"e_1_3_2_1_2_1","unstructured":"Anthropic. 2025. Claude 3.7 Sonnet System Card. https:\/\/assets.anthropic.com\/m\/785e231869ea8b3b\/original\/claude-3-7-sonnet-system-card.pdf"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/jcom.12276"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CTS.2009.5067498"},{"key":"e_1_3_2_1_5_1","volume-title":"Associations of gender and age groups on the knowledge and use of drug information resources by American pharmacists. Pharmacy practice","author":"Carvajal Manuel J","year":"2013","unstructured":"Manuel J Carvajal, Kevin A Clauson, Jennifer Gershman, and Hyla H Polen. 2013. Associations of gender and age groups on the knowledge and use of drug information resources by American pharmacists. Pharmacy practice, Vol. 11, 2 (2013), 71."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01520"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2022.3153167"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510579"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.954598"},{"key":"e_1_3_2_1_10_1","volume-title":"Medical Imaging 2009: Image Processing","author":"Goo\u00dfen Andr\u00e9","unstructured":"Andr\u00e9 Goo\u00dfen, Thomas Pralow, and Rolf-Rainer Grigat. 2009. Medical X-ray image enhancement by intra-image and inter-image similarity. In Medical Imaging 2009: Image Processing, Vol. 7259. SPIE, 162-171."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523273"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3560663"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20517"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2020.106260"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2022.12.019"},{"key":"e_1_3_2_1_16_1","volume-title":"Better zero-shot reasoning with role-play prompting. arXiv preprint arXiv:2308.07702","author":"Kong Aobo","year":"2023","unstructured":"Aobo Kong, Shiwan Zhao, Hao Chen, Qicheng Li, Yong Qin, Ruiqi Sun, Xin Zhou, Enzhi Wang, and Xiaohang Dong. 2023. Better zero-shot reasoning with role-play prompting. arXiv preprint arXiv:2308.07702 (2023)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2023.103448"},{"key":"e_1_3_2_1_18_1","volume-title":"Loogle: Can long-context language models understand long contexts? arXiv preprint arXiv:2311.04939","author":"Li Jiaqi","year":"2023","unstructured":"Jiaqi Li, Mengmeng Wang, Zilong Zheng, and Muhan Zhang. 2023b. Loogle: Can long-context language models understand long contexts? arXiv preprint arXiv:2311.04939 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Spatialpin: Enhancing spatial reasoning capabilities of vision-language models through prompting and interacting 3d priors. arXiv preprint arXiv:2403.13438","author":"Ma Chenyang","year":"2024","unstructured":"Chenyang Ma, Kai Lu, Ta-Ying Cheng, Niki Trigoni, and Andrew Markham. 2024. Spatialpin: Enhancing spatial reasoning capabilities of vision-language models through prompting and interacting 3d priors. arXiv preprint arXiv:2403.13438 (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/bsl.2166"},{"key":"e_1_3_2_1_21_1","volume-title":"Large language models: A survey. arXiv preprint arXiv:2402.06196","author":"Minaee Shervin","year":"2024","unstructured":"Shervin Minaee, Tomas Mikolov, Narjes Nikzad, Meysam Chenaghlu, Richard Socher, Xavier Amatriain, and Jianfeng Gao. 2024. Large language models: A survey. arXiv preprint arXiv:2402.06196 (2024)."},{"key":"e_1_3_2_1_22_1","unstructured":"OpenAI Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat Red Avila Igor Babuschkin Suchir Balaji Valerie Balcom Paul Baltescu et al. 2024. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_1_23_1","volume-title":"Mar\u00eda Jos\u00e9 Abell\u00e1n, and eVITAL group","author":"Salvador-Carulla Luis","year":"2013","unstructured":"Luis Salvador-Carulla, Federico Alonso, Rafael Gomez, Carolyn O Walsh, Jos\u00e9 Almenara, Menc\u00eda Ruiz, Mar\u00eda Jos\u00e9 Abell\u00e1n, and eVITAL group. 2013. Basic concepts in the taxonomy of health-related behaviors, habits and lifestyle. International journal of environmental research and public health, Vol. 10, 5 (2013), 1963-1976."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00963-y"},{"key":"e_1_3_2_1_25_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Staab Robin","year":"2023","unstructured":"Robin Staab, Mark Vero, Mislav Balunovic, and Martin Vechev. 2023. Beyond memorization: Violating privacy via inference with large language models. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.70.3.437"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2025.3534474"},{"key":"e_1_3_2_1_28_1","volume-title":"Threat modeling","author":"Swiderski Frank","unstructured":"Frank Swiderski and Window Snyder. 2004. Threat modeling. Microsoft Press."},{"key":"e_1_3_2_1_29_1","volume-title":"Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al.","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al., 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"Mai JM Chinapaw, Willem van Mechelen, and Henrica CW de Vet.","author":"Terwee Caroline B","year":"2010","unstructured":"Caroline B Terwee, Lidwine B Mokkink, Mireille NM van Poppel, Mai JM Chinapaw, Willem van Mechelen, and Henrica CW de Vet. 2010. Qualitative attributes and measurement properties of physical activity questionnaires: a checklist. Sports medicine, Vol. 40 (2010), 525-537."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-007-9055-5"},{"key":"e_1_3_2_1_32_1","volume-title":"Technologies, techniques, tools, and trends","author":"Thuraisingham Bhavani","unstructured":"Bhavani Thuraisingham and Data Maning. 1999. Technologies, techniques, tools, and trends. CRC press."},{"key":"e_1_3_2_1_33_1","unstructured":"Batuhan T\u00f6mek\u00e7e Mark Vero Robin Staab and Martin Vechev. 2024. Private attribute inference from images with vision-language models. In NeurIPS."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3014424"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.65"},{"key":"e_1_3_2_1_36_1","volume-title":"Exploring the reasoning abilities of multimodal large language models (mllms): A comprehensive survey on emerging trends in multimodal reasoning. arXiv preprint arXiv:2401.06805","author":"Wang Yiqi","year":"2024","unstructured":"Yiqi Wang, Wentao Chen, Xiaotian Han, Xudong Lin, Haiteng Zhao, Yongfei Liu, Bohan Zhai, Jianbo Yuan, Quanzeng You, and Hongxia Yang. 2024. Exploring the reasoning abilities of multimodal large language models (mllms): A comprehensive survey on emerging trends in multimodal reasoning. arXiv preprint arXiv:2401.06805 (2024)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19143052"},{"key":"e_1_3_2_1_38_1","volume-title":"Evaluation of human work","author":"Wilson John R","unstructured":"John R Wilson and Sarah Sharples. 2015. Evaluation of human work. CRC press."},{"key":"e_1_3_2_1_39_1","volume-title":"Inference attacks in machine learning as a service: A taxonomy, review, and promising directions. arXiv preprint arXiv:2406.02027","author":"Wu Feng","year":"2024","unstructured":"Feng Wu, Lei Cui, Shaowen Yao, and Shui Yu. 2024. Inference attacks in machine learning as a service: A taxonomy, review, and promising directions. arXiv preprint arXiv:2406.02027 (2024)."},{"key":"e_1_3_2_1_40_1","volume-title":"Vlm: Task-agnostic video-language model pre-training for video understanding. arXiv preprint arXiv:2105.09996","author":"Xu Hu","year":"2021","unstructured":"Hu Xu, Gargi Ghosh, Po-Yao Huang, Prahal Arora, Masoumeh Aminzadeh, Christoph Feichtenhofer, Florian Metze, and Luke Zettlemoyer. 2021. Vlm: Task-agnostic video-language model pre-training for video understanding. arXiv preprint arXiv:2105.09996 (2021)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418889"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICS51289.2020.00101"},{"key":"e_1_3_2_1_43_1","volume-title":"MM-LLMs: Recent advances in multimodal large language models. Findings of ACL","author":"Zhang Duzhen","year":"2024","unstructured":"Duzhen Zhang, Yahan Yu, Jiahua Dong, Chenxing Li, Dan Su, Chenhui Chu, and Dong Yu. 2024. MM-LLMs: Recent advances in multimodal large language models. Findings of ACL (2024)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533139"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.02.006"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP51992.2021.00025"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0164-1212(02)00064-X"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671462"},{"key":"e_1_3_2_1_49_1","volume-title":"Consensus of hybrid multi-agent systems","author":"Zheng Yuanshi","year":"2017","unstructured":"Yuanshi Zheng, Jingying Ma, and Long Wang. 2017. Consensus of hybrid multi-agent systems. IEEE transactions on neural networks and learning systems, Vol. 29, 4 (2017), 1359-1365."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00009"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:05:15Z","timestamp":1765343115000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755643"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":50,"alternative-id":["10.1145\/3746027.3755643","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755643","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}