{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:11:03Z","timestamp":1784139063407,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFB3106505"],"award-info":[{"award-number":["2023YFB3106505"]}]},{"name":"National Natural Science Foundation of China","award":["U24A20240"],"award-info":[{"award-number":["U24A20240"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809572","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"2556-2566","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["How Far Are We from Automatically Identifying Violations of the Data Minimization Principle in Privacy Policies?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9143-8385","authenticated-orcid":false,"given":"Ziyan","family":"Zhou","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9546-5043","authenticated-orcid":false,"given":"Yanru","family":"He","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and State Key Laboratory of Cyberspace Security Defense, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9611-5368","authenticated-orcid":false,"given":"Yunchuan","family":"Guo","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4428-5108","authenticated-orcid":false,"given":"Haoyang","family":"Yu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6448-5720","authenticated-orcid":false,"given":"Liang","family":"Fang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and State Key Laboratory of Cyberspace Security Defense, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0638-5610","authenticated-orcid":false,"given":"Fenghua","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2018. General Data Protection Regulation (GDPR). https:\/\/gdpr-info.eu\/"},{"key":"e_1_3_2_1_2_1","unstructured":"2020. The California Privacy Rights Act of 2020 (CPRA). https:\/\/thecpra.org\/"},{"key":"e_1_3_2_1_3_1","unstructured":"2021. Personal Information Protection Law of the People's Republic of China (PIPL). https:\/\/personalinformationprotectionlaw.com\/"},{"key":"e_1_3_2_1_4_1","unstructured":"2023. Ontology of Personal Information. https:\/\/opi.cs.cmu.edu\/"},{"key":"e_1_3_2_1_5_1","unstructured":"2024. The EU AI Act. https:\/\/artificialintelligenceact.eu\/"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2501.10319"},{"key":"e_1_3_2_1_7_1","first-page":"585","volume-title":"PolicyLint: Investigating Internal Privacy Policy Contradictions on Google Play. In 28th USENIX Security Symposium (USENIX Security 19)","author":"Andow Benjamin","year":"2019","unstructured":"Benjamin Andow, Samin Yaseer Mahmud, Wenyu Wang, Justin Whitaker, William Enck, Bradley Reaves, Kapil Singh, and Tao Xie. 2019. PolicyLint: Investigating Internal Privacy Policy Contradictions on Google Play. In 28th USENIX Security Symposium (USENIX Security 19). 585-602."},{"key":"e_1_3_2_1_8_1","unstructured":"Adrien Barbaresi. 2024. Trafilatura. https:\/\/pypi.org\/project\/trafilatura\/."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-49028-7_9"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401034"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3484536"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2402.03216"},{"key":"e_1_3_2_1_13_1","first-page":"1037","volume-title":"32nd USENIX Security Symposium (USENIX Security 23)","author":"Cui Hao","year":"2023","unstructured":"Hao Cui, Rahmadi Trimananda, Athina Markopoulou, and Scott Jordan. 2023. PoliGraph: Automated Privacy Policy Analysis using Knowledge Graphs. In 32nd USENIX Security Symposium (USENIX Security 23). 1037-1054."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671470"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732195"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2312.10997"},{"key":"e_1_3_2_1_17_1","unstructured":"Google. 2025. Google Play Store Categories. https:\/\/developers.apptweak.com\/reference\/google-play-store-categories"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.249"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1044"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"e_1_3_2_1_21_1","volume-title":"International Semantic Web Conference. 171-193","author":"Pandit Harshvardhan J.","year":"2024","unstructured":"Harshvardhan J. Pandit, Beatriz Esteves, Georg P. Krog, Paul Ryan, Delaram Golpayegani, and Julian Flake. 2024. Data Privacy Vocabulary (DPV)--Version 2.0. In International Semantic Web Conference. 171-193."},{"key":"e_1_3_2_1_22_1","unstructured":"Mingyu Jo. 2024. Google-play-scraper. https:\/\/pypi.org\/project\/google-play-scraper\/."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.fever-1.29"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.138"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.859"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.2478\/popets-2020-0004"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER60148.2024.00104"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"e_1_3_2_1_29_1","volume-title":"How Americans View Data Privacy","author":"McClain Colleen","year":"2023","unstructured":"Colleen McClain, Michelle Faverio, Monica Anderson, and Eugenie Park. 2023. How Americans View Data Privacy. Pew Research Center (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.56553\/popets-2023-0111"},{"key":"e_1_3_2_1_31_1","volume-title":"Context Engineering: Sessions & Memory. https:\/\/www.kaggle.com\/whitepaper-context-engineering-sessions-and-memory","author":"Milam Kimberly","year":"2025","unstructured":"Kimberly Milam and Antonio Gulli. 2025. Context Engineering: Sessions & Memory. https:\/\/www.kaggle.com\/whitepaper-context-engineering-sessions-and-memory"},{"key":"e_1_3_2_1_32_1","unstructured":"Kenneth Reitz. 2024. Requests. https:\/\/pypi.org\/project\/requests\/."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2057"},{"key":"e_1_3_2_1_34_1","first-page":"2797","volume-title":"33rd USENIX Security Symposium (USENIX Security 24)","author":"Sharma Tanusree","year":"2024","unstructured":"Tanusree Sharma, Lin Kyi, Yang Wang, and Asia J Biega. 2024. ''I'm not convinced that they don't collect more than is necessary'':{User-Controlled} Data Minimization Design in Search Engines. In 33rd USENIX Security Symposium (USENIX Security 24). 2797-2812."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.fever-1.10"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00530"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2508.10836"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00050"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.10238"},{"key":"e_1_3_2_1_40_1","first-page":"1","article-title":"Defining Privacy: How Users Interpret Technical Terms in Privacy Policies","volume":"3","author":"Tang Jenny","year":"2021","unstructured":"Jenny Tang, Hannah Shoemaker, Ada Lerner, and Eleanor Birrell. 2021. Defining Privacy: How Users Interpret Technical Terms in Privacy Policies. Proceedings on Privacy Enhancing Technologies 3 (2021), 1-25.","journal-title":"Proceedings on Privacy Enhancing Technologies"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00607-024-01331-9"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605762.3624435"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761587"},{"key":"e_1_3_2_1_44_1","first-page":"1091","volume-title":"Lalaine: Measuring and Characterizing Non-Compliance of Apple Privacy Labels. In 32nd USENIX Security Symposium (USENIX Security 23)","author":"Xiao Yue","year":"2023","unstructured":"Yue Xiao, Zhengyi Li, Yue Qin, Xiaolong Bai, Jiale Guan, Xiaojing Liao, and Luyi Xing. 2023. Lalaine: Measuring and Characterizing Non-Compliance of Apple Privacy Labels. In 32nd USENIX Security Symposium (USENIX Security 23). 1091-1108."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639107"},{"key":"e_1_3_2_1_46_1","first-page":"5797","volume-title":"34th USENIX Security Symposium (USENIX Security 25)","author":"Xie Qinge","year":"2025","unstructured":"Qinge Xie, Karthik Ramakrishnan, and Frank Li. 2025. Evaluating Privacy Policies under Modern Privacy Laws At Scale: An LLM-Based Automated Approach. In 34th USENIX Security Symposium (USENIX Security 25). 5797-5816."},{"key":"e_1_3_2_1_47_1","volume-title":"Quantifying Biases in LLM-as-a-Judge. In The Thirteenth International Conference on Learning Representations.","author":"Ye Jiayi","year":"2025","unstructured":"Jiayi Ye, Yanbo Wang, Yue Huang, Dongping Chen, Qihui Zhang, Nuno Moniz, Tian Gao, Werner Geyer, Chao Huang, Pin-Yu Chen, Nitesh V. Chawla, and Xiangliang Zhang. 2025. Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_48_1","volume-title":"Vetting Privacy Policies in VR: A Data Minimization Principle Perspective. In IEEE INFOCOM 2023-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). 1-2.","author":"Zhan Yuxia","year":"2023","unstructured":"Yuxia Zhan, Yan Meng, Lu Zhou, and Haojin Zhu. 2023. Vetting Privacy Policies in VR: A Data Minimization Principle Perspective. In IEEE INFOCOM 2023-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). 1-2."},{"key":"e_1_3_2_1_49_1","volume-title":"How Android Apps Break the Data Minimization Principle: An Empirical Study. In 2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE). 1238-1250","author":"Zhang Shaokun","year":"2023","unstructured":"Shaokun Zhang, Hanwen Lei, Yuanpeng Wang, Ding Li, Yao Guo, and Xiangqun Chen. 2023. How Android Apps Break the Data Minimization Principle: An Empirical Study. In 2023 38th IEEE\/ACM International Conference on Automated Software Engineering (ASE). 1238-1250."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"e_1_3_2_1_51_1","first-page":"1073","volume-title":"32nd USENIX Security Symposium (USENIX Security 23)","author":"Zhou Lu","year":"2023","unstructured":"Lu Zhou, Chengyongxiao Wei, Tong Zhu, Guoxing Chen, Xiaokuan Zhang, Suguo Du, Hui Cao, and Haojin Zhu. 2023. {POLICYCOMP}: Counterpart Comparison of Privacy Policies Uncovers Overbroad Personal Data Collection Practices. In 32nd USENIX Security Symposium (USENIX Security 23). 1073-1090."},{"key":"e_1_3_2_1_52_1","volume-title":"Automated Analysis of Privacy Requirements for Mobile Apps. In 24th Annual Network and Distributed System Security Symposium.","author":"Zimmeck Sebastian","unstructured":"Sebastian Zimmeck, Ziqi Wang, Lieyong Zou, Roger Iyengar, Bin Liu, Florian Schaub, Shomir Wilson, Norman M. Sadeh, Steven M. Bellovin, and Joel R. Reidenberg. 2017. Automated Analysis of Privacy Requirements for Mobile Apps. In 24th Annual Network and Distributed System Security Symposium."}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:29:44Z","timestamp":1784136584000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809572"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":52,"alternative-id":["10.1145\/3805712.3809572","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809572","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}