{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:18:47Z","timestamp":1778080727602,"version":"3.51.4"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031926471","type":"print"},{"value":"9783031926488","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-92648-8_26","type":"book-chapter","created":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T16:28:22Z","timestamp":1748622502000},"page":"435-451","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["The Phantom Menace: Unmasking Privacy Leakages in\u00a0Vision-Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0263-4781","authenticated-orcid":false,"given":"Simone","family":"Caldarella","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8595-9955","authenticated-orcid":false,"given":"Massimiliano","family":"Mancini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0228-1147","authenticated-orcid":false,"given":"Elisa","family":"Ricci","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9871-6458","authenticated-orcid":false,"given":"Rahaf","family":"Aljundi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"26_CR1","unstructured":"AI, J.: Easy ocr (2022). https:\/\/github.com\/JaidedAI\/EasyOCR"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., Tuytelaars, T.: Memory aware synapses: learning what (not) to forget. In: Proceedings of the European Conference on computer Vision (ECCV), pp. 139\u2013154 (2018)","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: Vqa: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"26_CR4","unstructured":"Balloccu, S., Schmidtov\u00e1, P., Lango, M., Du\u0161ek, O.: Leak, cheat, repeat: data contamination and evaluation malpractices in closed-source llms. arXiv preprint arXiv:2402.03927 (2024)"},{"key":"26_CR5","unstructured":"Beyer, L., et\u00a0al.: Paligemma: a versatile 3b vlm for transfer. arXiv preprint arXiv:2407.07726 (2024)"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Cao, M., Li, S., Li, J., Nie, L., Zhang, M.: Image-text retrieval: a survey on recent research and development. arXiv preprint arXiv:2203.14713 (2022)","DOI":"10.24963\/ijcai.2022\/759"},{"key":"26_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmcj.2023.101801","volume":"92","author":"M Cardaioli","year":"2023","unstructured":"Cardaioli, M., Conti, M., Orazi, G., Tricomi, P.P., Tsudik, G.: Blufader: blurred face detection & recognition for privacy-friendly continuous authentication. Perv. Mob. Comput. 92, 101801 (2023)","journal-title":"Perv. Mob. Comput."},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12 m: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3558\u20133568 (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"26_CR9","unstructured":"Chiang, W.L., et\u00a0al.: Vicuna: an open-source chatbot impressing gpt-4 with 90%* chatgpt quality, 2(3), 6 (2023). See https:\/\/vicuna.lmsys.org. Accessed 14 Apr 2023"},{"key":"26_CR10","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"26_CR11","unstructured":"Duan, S., Khona, M., Iyer, A., Schaeffer, R., Fiete, I.R.: Uncovering latent memories: assessing data leakage and memorization patterns in large language models. arXiv preprint arXiv:2406.14549 (2024)"},{"key":"26_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/11787006_1","volume-title":"Automata, Languages and Programming","author":"C Dwork","year":"2006","unstructured":"Dwork, C.: Differential privacy. In: Bugliesi, M., Preneel, B., Sassone, V., Wegener, I. (eds.) ICALP 2006. LNCS, vol. 4052, pp. 1\u201312. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11787006_1"},{"key":"26_CR13","unstructured":"European Parliament, Council of the European Union: Regulation (EU) 2016\/679 of the European Parliament and of the Council (2016). https:\/\/data.europa.eu\/eli\/reg\/2016\/679\/oj"},{"key":"26_CR14","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1613\/jair.1.15461","volume":"80","author":"D Hintersdorf","year":"2024","unstructured":"Hintersdorf, D., Struppek, L., Brack, M., Friedrich, F., Schramowski, P., Kersting, K.: Does clip know my face? J. Artif. Intell. Res. 80, 1033\u20131062 (2024)","journal-title":"J. Artif. Intell. Res."},{"issue":"6","key":"26_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3295748","volume":"51","author":"MZ Hossain","year":"2019","unstructured":"Hossain, M.Z., Sohel, F., Shiratuddin, M.F., Laga, H.: A comprehensive survey of deep learning for image captioning. ACM Comput. Surv. (CsUR) 51(6), 1\u201336 (2019)","journal-title":"ACM Comput. Surv. (CsUR)"},{"key":"26_CR16","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"26_CR17","unstructured":"Jiang, A.Q., et\u00a0al.: Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024)"},{"issue":"23","key":"26_CR18","doi-asserted-by":"publisher","first-page":"9376","DOI":"10.3390\/s22239376","volume":"22","author":"J Jiang","year":"2022","unstructured":"Jiang, J., Skalli, W., Siadat, A., Gajny, L.: Effect of face blurring on human pose estimation: ensuring subject privacy for medical and occupational health applications. Sensors 22(23), 9376 (2022)","journal-title":"Sensors"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"26_CR20","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Li, N., Li, T., Venkatasubramanian, S.: t-closeness: privacy beyond k-anonymity and l-diversity. In: 2007 IEEE 23rd International Conference on Data Engineering, pp. 106\u2013115. IEEE (2006)","DOI":"10.1109\/ICDE.2007.367856"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Li, T., Lin, L.: Anonymousnet: natural face de-identification with measurable privacy. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00013"},{"issue":"12","key":"26_CR23","doi-asserted-by":"publisher","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","volume":"40","author":"Z Li","year":"2017","unstructured":"Li, Z., Hoiem, D.: Learning without forgetting. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2935\u20132947 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"26_CR25","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding dino: marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Machanavajjhala, A., Kifer, D., Gehrke, J., Venkitasubramaniam, M.: l-diversity: privacy beyond k-anonymity. ACM Trans. Knowl. Disc. Data (TKDD) 1(1), 3\u2013es (2007)","DOI":"10.1145\/1217299.1217302"},{"key":"26_CR28","unstructured":"Maini, P., Mozer, M.C., Sedghi, H., Lipton, Z.C., Kolter, J.Z., Zhang, C.: Can neural network memorization be localized? arXiv preprint arXiv:2307.09542 (2023)"},{"key":"26_CR29","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics. pp. 1273\u20131282. PMLR (2017)"},{"key":"26_CR30","unstructured":"Microsoft: Github copilot (2024). https:\/\/github.com\/features\/copilot. Accessed 22 June 2024"},{"key":"26_CR31","unstructured":"OpenAI: Chatgpt (2023). https:\/\/chatgpt.com\/, june 2024 version"},{"key":"26_CR32","unstructured":"OpenAI: Our approach to AI safety (2024). https:\/\/openai.com\/index\/our-approach-to-ai-safety\/. Accessed 19 July 2024"},{"key":"26_CR33","unstructured":"Papernot, N., Song, S., Mironov, I., Raghunathan, A., Talwar, K., Erlingsson, \u00da.: Scalable private learning with pate. arXiv preprint arXiv:1802.08908 (2018)"},{"key":"26_CR34","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"140","key":"26_CR35","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"26_CR36","unstructured":"Samarati, P., Sweeney, L.: Protecting privacy when disclosing information: k-anonymity and its enforcement through generalization and suppression (1998)"},{"key":"26_CR37","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, vol. 1: Long Papers, pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"26_CR39","unstructured":"State of California: California consumer privacy act. California Civil Code, Title 1.81.5, Sections 1798.100-1798.199 (2018). https:\/\/oag.ca.gov\/privacy\/ccpa"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Suhr, A., Zhou, S., Zhang, A., Zhang, I., Bai, H., Artzi, Y.: A corpus for reasoning about natural language grounded in photographs. arXiv preprint arXiv:1811.00491 (2018)","DOI":"10.18653\/v1\/P19-1644"},{"key":"26_CR41","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"26_CR42","unstructured":"Ultralytics: Yolov8-face (2024). https:\/\/github.com\/akanametov\/yolo-face. Accessed 22 June 2024"},{"key":"26_CR43","unstructured":"Verwimp, E., et\u00a0al.: Continual learning: applications and the road forward. Trans. Mach. Learn. Res. (2023)"},{"issue":"2","key":"26_CR44","first-page":"102","volume":"2","author":"X Wu","year":"2024","unstructured":"Wu, X., Duan, R., Ni, J.: Unveiling security, privacy, and ethical concerns of chatgpt. J. Inf. Intell. 2(2), 102\u2013115 (2024)","journal-title":"J. Inf. Intell."},{"key":"26_CR45","unstructured":"Zeng, Y., Zhang, X., Li, H.: Multi-grained vision language pre-training: aligning texts with visual concepts. arXiv preprint arXiv:2111.08276 (2021)"},{"key":"26_CR46","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"26_CR47","unstructured":"Zhang, S., et\u00a0al.: Opt: open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)"},{"key":"26_CR48","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"},{"issue":"1","key":"26_CR49","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1057\/jit.2015.5","volume":"30","author":"S Zuboff","year":"2015","unstructured":"Zuboff, S.: Big other: surveillance capitalism and the prospects of an information civilization. J. Inf. Technol. 30(1), 75\u201389 (2015)","journal-title":"J. Inf. Technol."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-92648-8_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T16:28:52Z","timestamp":1748622532000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-92648-8_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031926471","9783031926488"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-92648-8_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}