{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T03:46:53Z","timestamp":1770695213762,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569564","type":"print"},{"value":"9789819569571","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\/978-981-95-6957-1_3","type":"book-chapter","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T10:44:10Z","timestamp":1770633850000},"page":"31-44","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Auditing M-LLMs for\u00a0Privacy Risks: A Synthetic Benchmark and\u00a0Evaluation Framework"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1233-2236","authenticated-orcid":false,"given":"Junhao","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5894-662X","authenticated-orcid":false,"given":"Jiahao","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5301-7019","authenticated-orcid":false,"given":"Zhou","family":"Feng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0081-0946","authenticated-orcid":false,"given":"Chunyi","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,10]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","DOI":"10.2196\/59505","volume":"26","author":"R AlSaad","year":"2024","unstructured":"AlSaad, R., et al.: Multimodal large language models in health care: applications, challenges, and future outlook. J. Med. Internet Res. 26, e59505 (2024). https:\/\/doi.org\/10.2196\/59505","journal-title":"J. Med. Internet Res."},{"key":"3_CR2","unstructured":"Bai, J., et al.: Qwen2: a family of large-scale language models. arXiv preprint arXiv:2406.04832 (2024)"},{"key":"3_CR3","unstructured":"ByteDance: Doubao-llm (2024). https:\/\/www.volcengine.com\/product\/doubao-llm"},{"key":"3_CR4","unstructured":"DataReportal: Digital 2024: Global overview report (2024). https:\/\/datareportal.com\/reports\/digital-2024-global-overview-report. Accessed 16 Aug 2025"},{"key":"3_CR5","unstructured":"Fang, J., et al.: SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models. arXiv preprint (2025)"},{"key":"3_CR6","doi-asserted-by":"publisher","unstructured":"Feng, Z., et al.: Enkidu: universal frequential perturbation for real-time audio privacy protection against voice deepfakes. In: Proceedings of the 33rd ACM International Conference on Multimedia (MM 2025), pp. 11638\u201311647. Association for Computing Machinery, New York (2025). https:\/\/doi.org\/10.1145\/3746027.3755629","DOI":"10.1145\/3746027.3755629"},{"key":"3_CR7","unstructured":"Gan, Y., et al.: Navigating the risks: a survey of security, privacy, and ethics threats in LLM-based agents (2024). https:\/\/arxiv.org\/abs\/2411.09523"},{"key":"3_CR8","unstructured":"Ge, Y., Kirtane, N., Peng, H., Hakkani-T\u00fcr, D.: LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language. arXiv preprint (2025)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Haas, L., Skreta, M., Alberti, S., Finn, C.: PIGEON: Predicting Image Geolocations. arXiv preprint (2024)","DOI":"10.1109\/CVPR52733.2024.01225"},{"issue":"8","key":"3_CR10","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-025-4388-5","volume":"68","author":"X He","year":"2025","unstructured":"He, X., et al.: Artificial intelligence security and privacy: a survey. SCIENCE CHINA Inf. Sci. 68(8), 181101 (2025). https:\/\/doi.org\/10.1007\/s11432-025-4388-5","journal-title":"SCIENCE CHINA Inf. Sci."},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Li, J., Ji, R., Liu, H., Hong, X., Gao, Y., Tian, Q.: Universal perturbation attack against image retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00500"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Lin, T., et al.: Microsoft COCO: common objects in context. CoRR (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Liu, F., et al.: The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework. arXiv preprint (2025)","DOI":"10.1145\/3746027.3755643"},{"key":"3_CR14","doi-asserted-by":"publisher","unstructured":"Luo, W., et al.: Dynamic guided and domain applicable safeguards for enhanced security in large language models. In: Findings of the Association for Computational Linguistics: NAACL 2025, pp. 6599\u20136620. Association for Computational Linguistics (2025). https:\/\/doi.org\/10.18653\/V1\/2025.FINDINGS-NAACL.368","DOI":"10.18653\/V1\/2025.FINDINGS-NAACL.368"},{"key":"3_CR15","unstructured":"Luo, W., et al.: Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models. arXiv preprint (2025)"},{"key":"3_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/J.ESWA.2025.127270","volume":"280","author":"E Novikova","year":"2025","unstructured":"Novikova, E., Doynikova, E., Kotenko, I.V.: What are your privacy risks? Privacy risk assessment based on privacy policies analysis. Expert Syst. Appl. 280, 127270 (2025). https:\/\/doi.org\/10.1016\/J.ESWA.2025.127270","journal-title":"Expert Syst. Appl."},{"key":"3_CR17","doi-asserted-by":"publisher","unstructured":"Oh, S.J., Fritz, M., Schiele, B.: Adversarial image perturbation for privacy protection: a game theory perspective. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1491\u20131500 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.165","DOI":"10.1109\/ICCV.2017.165"},{"key":"3_CR18","unstructured":"OpenAI: Gpt-4o technical report. arXiv preprint arXiv:2405.20712 (2024)"},{"key":"3_CR19","unstructured":"Pawelczyk, M., Neel, S., Lakkaraju, H.: In-context unlearning: language models as few shot unlearners (2024)"},{"issue":"5","key":"3_CR20","doi-asserted-by":"publisher","first-page":"5186","DOI":"10.1109\/TDSC.2025.3563477","volume":"22","author":"Y Pu","year":"2025","unstructured":"Pu, Y., Chen, J., Pan, J., Yan, D., Zhang, X., Ji, S.: Facial data minimization: shallow model as your privacy filter. IEEE Trans. Dependable Secure Comput. 22(5), 5186\u20135202 (2025). https:\/\/doi.org\/10.1109\/TDSC.2025.3563477","journal-title":"IEEE Trans. Dependable Secure Comput."},{"key":"3_CR21","unstructured":"Staab, R., Vero, M., Balunovi\u0107, M., Vechev, M.: Beyond Memorization: Violating Privacy Via Inference with Large Language Models. arXiv preprint (2024)"},{"key":"3_CR22","unstructured":"Team, G., Google: Gemini: A family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"3_CR23","unstructured":"Wang, L., et al.: The man behind the sound: demystifying audio private attribute profiling via multimodal large language model agents (2025). https:\/\/arxiv.org\/abs\/2507.10016"},{"key":"3_CR24","unstructured":"Wang, S., Hu, M., Li, Q., Safari, M., Yang, X.: Capabilities of GPT-5 on Multimodal Medical Reasoning. arXiv preprint (2025)"},{"key":"3_CR25","unstructured":"xAI: Announcing grok (2023). https:\/\/x.ai\/blog\/grok"},{"key":"3_CR26","unstructured":"Xu, W., Fan, W., Lu, S., Li, T., Wang, B.: Polarized Patterns of Language Toxicity and Sentiment of Debunking Posts on Social Media. arXiv preprint (2025)"},{"key":"3_CR27","doi-asserted-by":"publisher","first-page":"6101","DOI":"10.1109\/TIFS.2025.3579592","volume":"20","author":"Y Yang","year":"2025","unstructured":"Yang, Y., et al.: Invisible-face: rethinking facial attribute privacy in social media photo sharing. IEEE Trans. Inf. Forensics Secur. 20, 6101\u20136116 (2025). https:\/\/doi.org\/10.1109\/TIFS.2025.3579592","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"3_CR28","unstructured":"Yu, Z., Liu, X., Liang, S., Cameron, Z., Xiao, C., Zhang, N.: Don\u2019t listen to me: understanding and exploring jailbreak prompts of large language models. In: 33rd USENIX Security Symposium (USENIX Security 2024), pp. 4675\u20134692. USENIX Association, Philadelphia, PA (2024)"},{"issue":"3","key":"3_CR29","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1109\/TKDE.2023.3295601","volume":"36","author":"S Zhang","year":"2024","unstructured":"Zhang, S., Yuan, W., Yin, H.: Comprehensive privacy analysis on federated recommender system against attribute inference attacks. IEEE Trans. Knowl. Data Eng. 36(3), 987\u2013999 (2024). https:\/\/doi.org\/10.1109\/TKDE.2023.3295601","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"3_CR30","unstructured":"Zheng Xiao\u00a0Du, Yujie\u00a0Qian, X.L., et\u00a0al.: Glm-4: An open bilingual multimodal large model. arXiv preprint arXiv:2405.19793 (2024)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6957-1_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T10:44:15Z","timestamp":1770633855000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6957-1_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569564","9789819569571"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6957-1_3","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 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","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":"29 January 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2026.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}