Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
通过镜头进行Doxing:揭示多模态大推理模型中的位置相关隐私泄露
机构 * University of Georgia(佐治亚大学) ; University of Wisconsin–Madison(威斯康星大学麦迪逊分校) ; John Hopkins University(约翰·霍普金斯大学) ; University of Southern California(南加州大学) ; University of Maryland, College Park(马里兰大学学院市分校)
AI总结 本文研究了多模态大推理模型中的位置隐私泄露问题,提出DoxBench和GeoMiner框架,揭示模型在推断地理位置信息上的能力及隐私风险。
Comments Camera-ready version. Accepted as a poster at the 14th International Conference on Learning Representations (ICLR 2026). For official ICLR page, see https://iclr.cc/virtual/2026/poster/10006914