{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T20:52:06Z","timestamp":1792183926432,"version":"4.4.0"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370976","type":"print"},{"value":"9783032370983","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\/978-3-032-37098-3_30","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T09:04:10Z","timestamp":1788944650000},"page":"547-565","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["GEO-Detective: Unveiling Location Privacy Risks in\u00a0Images with\u00a0LLM Agents"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6451-0121","authenticated-orcid":false,"given":"Xinyu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3000-9423","authenticated-orcid":false,"given":"Yixin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5403-1283","authenticated-orcid":false,"given":"Boyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6265-7345","authenticated-orcid":false,"given":"Chenhao","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6959-0569","authenticated-orcid":false,"given":"Chao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7130-9211","authenticated-orcid":false,"given":"Michael","family":"Backes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3612-7348","authenticated-orcid":false,"given":"Yang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"30_CR1","unstructured":"Flickr. https:\/\/flickr.com. Accessed 30 June 2026"},{"key":"30_CR2","unstructured":"Gemini Flash. https:\/\/docs.cloud.google.com\/vertex-ai\/generative-ai\/docs\/models\/gemini\/2-5-flash. Accessed 30 June 2026"},{"key":"30_CR3","unstructured":"Gemini Pro. https:\/\/docs.cloud.google.com\/vertex-ai\/generative-ai\/docs\/models\/gemini\/2-5-pro. Accessed 30 June 2026"},{"key":"30_CR4","unstructured":"YOLOv5. https:\/\/zenodo.org\/record\/6222936. Accessed 30 June 2026"},{"key":"30_CR5","unstructured":"John McAfee\u2019s location inadvertently revealed by photo metadata (2012). https:\/\/www.theguardian.com\/world\/2012\/dec\/03\/john-mcafee-location-revealed-vice. Accessed 30 June 2026"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Cepeda, V.V., Nayak, G.K., Shah, M.: GeoCLIP: CLIP-inspired alignment between locations and images for effective worldwide geo-localization. In: Annual Conference on Neural Information Processing Systems (NeurIPS), pp. 8690\u20138701. NeurIPS (2023)","DOI":"10.52202\/075280-0379"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Chen, T., Li, P., Zhou, K., Chen, T., Wei, H.: Unveiling privacy risks in multi-modal large language models: task-specific vulnerabilities and mitigation challenges. In: Annual Meeting of the Association for Computational Linguistics (ACL), pp. 4573\u20134586. ACL (2025)","DOI":"10.18653\/v1\/2025.findings-acl.237"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Deng, A., Cao, T., Chen, Z., Hooi, B.: Words or vision: do vision-language models have blind faith in text? In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2025)","DOI":"10.1109\/CVPR52734.2025.00366"},{"key":"30_CR9","unstructured":"Future, B.: The Hidden Fingerprint Inside Your Photos. https:\/\/www.bbc.co.uk\/future\/article\/20210324-the-hidden-fingerprint-inside-your-photos. Accessed 30 June 2026"},{"key":"30_CR10","unstructured":"Haas, L., Alberti, S., Skreta, M.: Learning generalized zero-shot learners for open-domain image geolocalization. CoRR abs\/2302.00275 (2023)"},{"key":"30_CR11","doi-asserted-by":"publisher","unstructured":"Haas, L., Skreta, M., Alberti, S., Finn, C.: PIGEON: predicting image geolocations. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, 16\u201322 June 2024, pp. 12893\u201312902. IEEE (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01225","DOI":"10.1109\/CVPR52733.2024.01225"},{"key":"30_CR12","doi-asserted-by":"publisher","unstructured":"Han, X., Zhu, C., Zhu, H., Zhao, X.: Swarm intelligence in geo-localization: a multi-agent large vision-language model collaborative framework. In: Antonie, L., et al. (eds.) Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, V.2, KDD 2025, Toronto ON, Canada, 3\u20137 August 2025, pp. 814\u2013825. ACM (2025). https:\/\/doi.org\/10.1145\/3711896.3737141","DOI":"10.1145\/3711896.3737141"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Hays, J., Efros, A.A.: IM2GPS: estimating geographic information from a single image. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587784"},{"key":"30_CR14","unstructured":"Huang, J., Huang, J., Liu, Z., Liu, X., Wang, W., Zhao, J.: VLMs as geoguessr masters: exceptional performance, hidden biases,and privacy risks. CoRR abs\/2502.11163 (2025)"},{"key":"30_CR15","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning (ICML), pp. 4904\u20134916. PMLR (2021)"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Jia, P., et al.: G3: an effective and adaptive framework for worldwide geolocalization using large multi-modality models. In: Annual Conference on Neural Information Processing Systems (NeurIPS), pp. 53198\u201353221. NeurIPS (2024)","DOI":"10.52202\/079017-1685"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Jia, P., Park, S., Gao, S., Zhao, X., Li, Y.: GeoRanker: distance-aware ranking for worldwide image geolocalization. CoRR abs\/2505.13731 (2025)","DOI":"10.52202\/085713-0596"},{"key":"30_CR18","unstructured":"Jiang, Q., Chen, X., Zeng, Z., Yu, J., Zhang, L.: Rex-thinker: grounded object referring via chain-of-thought reasoning. CoRR abs\/2506.04034 (2025)"},{"key":"30_CR19","unstructured":"Li, L., Ye, Y., Jiang, B., Zeng, W.: GeoReasoner: geo-localization with reasoning in street views using a large vision-language model. In: Salakhutdinov, R., et al. (eds.) Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, 21\u201327 July 2024. Proceedings of Machine Learning Research, vol.\u00a0235, pp. 29222\u201329233. PMLR\/OpenReview.net (2024). https:\/\/proceedings.mlr.press\/v235\/li24ch.html"},{"key":"30_CR20","doi-asserted-by":"publisher","unstructured":"Liang, J., et al.: VL-trojan: multimodal instruction backdoor attacks against autoregressive visual language models. CoRR abs\/2402.13851 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2402.13851","DOI":"10.48550\/ARXIV.2402.13851"},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual Instruction Tuning. In: Annual Conference on Neural Information Processing Systems (NeurIPS). NeurIPS (2023)","DOI":"10.52202\/075280-1516"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Liu, X., Zhu, Y., Lan, Y., Yang, C., Qiao, Y.: Safety of multimodal large language models on images and text. In: International Joint Conferences on Artifical Intelligence (IJCAI), pp. 8151\u20138159. IJCAI (2024)","DOI":"10.24963\/ijcai.2024\/901"},{"key":"30_CR23","doi-asserted-by":"publisher","unstructured":"Liu, Y., et al.: Mission: impossible - image-based geolocation with large vision language models. Proc. Priv. Enhanc. Technol. 2025(4), 410\u2013428 (2025). https:\/\/doi.org\/10.56553\/POPETS-2025-0137","DOI":"10.56553\/POPETS-2025-0137"},{"key":"30_CR24","unstructured":"Liu, Y., et al.: Image-based geolocation using large vision-language models. CoRR abs\/2408.09474 (2024)"},{"key":"30_CR25","unstructured":"Luo, W., et al.: Doxing via the lens: revealing privacy leakage in image geolocation for agentic multi-modal large reasoning model. CoRR abs\/2504.19373 (2025)"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Lyu, W., Pang, L., Ma, T., Ling, H., Chen, C.: TrojVLM: backdoor attack against vision language models. In: European Conference on Computer Vision (ECCV), pp. 467\u2013483. Springer (2024)","DOI":"10.1007\/978-3-031-73650-6_27"},{"key":"30_CR27","unstructured":"Mai, G., Lao, N., He, Y., Song, J., Ermon, S.: CSP: self-supervised contrastive spatial pre-training for geospatial-visual representations. In: International Conference on Machine Learning (ICML). PMLR (2023)"},{"key":"30_CR28","doi-asserted-by":"crossref","unstructured":"Mendes, E., Chen, Y., Hays, J., Das, S., Xu, W., Ritter, A.: Granular privacy control for geolocation with vision language models. In: Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 17240\u201317292. ACL (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.957"},{"key":"30_CR29","unstructured":"Mink, J., Luo, L., Barbosa, N.M., Figueira, O., Wang, Y., Wang, G.: DeepPhish: understanding user trust towards artificially generated profiles in online social networks. In: USENIX Security Symposium (USENIX Security), pp. 1669\u20131686. USENIX (2022)"},{"key":"30_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1007\/978-3-030-01258-8_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"E M\u00fcller-Budack","year":"2018","unstructured":"M\u00fcller-Budack, E., Pustu-Iren, K., Ewerth, R.: Geolocation estimation of photos using a hierarchical model and scene classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 575\u2013592. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01258-8_35"},{"key":"30_CR31","unstructured":"OpenAI: GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/. Accessed 30 June 2026"},{"key":"30_CR32","unstructured":"OpenAI: o3. https:\/\/platform.openai.com\/docs\/models\/o3. Accessed 30 June 2026"},{"key":"30_CR33","doi-asserted-by":"crossref","unstructured":"Orekondy, T., Schiele, B., Fritz, M.: Towards a visual privacy advisor: understanding and predicting privacy risks in images. In: IEEE International Conference on Computer Vision (ICCV), pp. 3706\u20133715. IEEE (2017)","DOI":"10.1109\/ICCV.2017.398"},{"key":"30_CR34","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML), pp. 8748\u20138763. PMLR (2021)"},{"key":"30_CR35","doi-asserted-by":"crossref","unstructured":"Roy, P.C., Boddeti, V.N.: Mitigating information leakage in image representations: a maximum entropy approach. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2586\u20132594. IEEE (2019)","DOI":"10.1109\/CVPR.2019.00269"},{"key":"30_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1007\/978-3-030-01249-6_33","volume-title":"Computer Vision \u2013 ECCV 2018","author":"PH Seo","year":"2018","unstructured":"Seo, P.H., Weyand, T., Sim, J., Han, B.: CPlaNet: enhancing image geolocalization by combinatorial partitioning of maps. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 544\u2013560. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_33"},{"key":"30_CR37","doi-asserted-by":"crossref","unstructured":"Shen, Y., Song, K., Tan, X., Li, D., Lu, W., Zhuang, Y.: HuggingGPT: solving AI tasks with ChatGPT and its friends in hugging face. In: Annual Conference on Neural Information Processing Systems (NeurIPS), pp. 38154\u201338180. NeurIPS (2023)","DOI":"10.52202\/075280-1657"},{"key":"30_CR38","unstructured":"Song, Z., et al.: Geolocation with real human gameplay data: a large-scale dataset and human-like reasoning framework. CoRR abs\/2502.13759 (2025)"},{"key":"30_CR39","doi-asserted-by":"crossref","unstructured":"Su, J., Kempe, J., Ullrich, K.: Mission impossible: a statistical perspective on jailbreaking LLMs. CoRR abs\/2408.01420 (2024)","DOI":"10.52202\/079017-1210"},{"key":"30_CR40","unstructured":"Suresh, S., Chodosh, N., Abello, M.: DeepGeo: photo localization with deep neural network. CoRR abs\/1810.03077 (2018)"},{"key":"30_CR41","doi-asserted-by":"crossref","unstructured":"T\u00f6mek\u00e7e, B.B., Vero, M., Staab, R., Vechev, M.T.: Private attribute inference from images with vision-language models. In: Annual Conference on Neural Information Processing Systems (NeurIPS), pp. 103619\u2013103651. NeurIPS (2024)","DOI":"10.52202\/079017-3291"},{"key":"30_CR42","doi-asserted-by":"publisher","unstructured":"Vo, N.N., Jacobs, N., Hays, J.: Revisiting IM2GPS in the deep learning era. In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, 22\u201329 October 2017, pp. 2640\u20132649. IEEE Computer Society (2017).https:\/\/doi.org\/10.1109\/ICCV.2017.286","DOI":"10.1109\/ICCV.2017.286"},{"key":"30_CR43","unstructured":"Wang, H., Ma, Q.: Textural or textual: how vision-language models read text in images. In: International Conference on Machine Learning (ICML). PMLR (2025)"},{"key":"30_CR44","doi-asserted-by":"crossref","unstructured":"Wang, K., Huang, Y., M., Gool, J.O., Tuytelaars, L.V., T.: An analysis of human-centered geolocation. In: Winter Conference on Applications of Computer Vision (WACV), pp. 2058\u20132066. IEEE (2018)","DOI":"10.1109\/WACV.2018.00227"},{"key":"30_CR45","unstructured":"Wang, Z., Xu, D., Khan, R.M.S., Lin, Y., Fan, Z., Zhu, X.: LLMGeo: benchmarking large language models on image geolocation in-the-wild. CoRR abs\/2405.20363 (2024)"},{"key":"30_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/978-3-319-46484-8_3","volume-title":"Computer Vision \u2013 ECCV 2016","author":"T Weyand","year":"2016","unstructured":"Weyand, T., Kostrikov, I., Philbin, J.: PlaNet - photo geolocation with convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 37\u201355. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_3"},{"key":"30_CR47","unstructured":"Wu, C., Yin, S., Qi, W., Wang, X., Tang, Z., Duan, N.: Visual ChatGPT: talking, drawing and editing with visual foundation models. CoRR abs\/2303.04671 (2023)"},{"key":"30_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1007\/978-3-319-26362-5_20","volume-title":"Research in Attacks, Intrusions, and Defenses","author":"H Xu","year":"2015","unstructured":"Xu, H., Wang, H., Stavrou, A.: Privacy risk assessment on online photos. In: Bos, H., Monrose, F., Blanc, G. (eds.) RAID 2015. LNCS, vol. 9404, pp. 427\u2013447. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-26362-5_20"},{"key":"30_CR49","doi-asserted-by":"crossref","unstructured":"Yang, Y., Wang, S., Li, D., Sun, S., Wu, Q.: GeoLocator: a location-integrated large multimodal model (LMM) for inferring geo-privacy. Appl. Sci. (2024)","DOI":"10.3390\/app14167091"},{"key":"30_CR50","unstructured":"Yao, S., et al.: ReAct: synergizing reasoning and acting in language models. In: International Conference on Learning Representations (ICLR). ICLR (2023)"},{"key":"30_CR51","doi-asserted-by":"crossref","unstructured":"Yerramilli, S., Pande, N., Grover, R., Tamarapalli, J.S.: GeoChain: multimodal chain-of-thought for geographic reasoning. CoRR abs\/2506.00785 (2025)","DOI":"10.18653\/v1\/2025.findings-emnlp.1284"},{"key":"30_CR52","doi-asserted-by":"crossref","unstructured":"Zheng, Y., et al.: Tour the world: building a web-scale landmark recognition engine. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1085\u20131092. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206749"},{"key":"30_CR53","doi-asserted-by":"publisher","unstructured":"Zhou, Z., et al.: Img2loc: revisiting image geolocalization using multi-modality foundation models and image-based retrieval-augmented generation. In: Yang, G.H., Wang, H., Han, S., Hauff, C., Zuccon, G., Zhang, Y. (eds.) Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2024, Washington DC, USA, 14\u201318 July 2024, pp. 2749\u20132754. ACM (2024). https:\/\/doi.org\/10.1145\/3626772.3657673","DOI":"10.1145\/3626772.3657673"},{"key":"30_CR54","unstructured":"Zhu, R.: Text prompt injection of vision language models. CoRR abs\/2510.09849 (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\/978-3-032-37098-3_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:16:58Z","timestamp":1792023418000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37098-3_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370976","9783032370983"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37098-3_30","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":"10 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"}}]}}