利用视觉语言模型实现地理定位的细粒度隐私控制
Granular Privacy Control for Geolocation with Vision Language Models
AI总结：
本文针对视觉语言模型带来的地理定位隐私风险，构建了 GPTGeoChat 基准并收集 1000 组带粒度标注的对话，发现微调模型在细粒度位置信息审核上优于提示式 API 模型。
摘要：
视觉语言模型（VLMs）在回答信息查询问题方面的能力正在迅速提升。随着这些模型被广泛部署于消费级应用中，由于其在识别人物、定位图像等方面涌现出的能力，它们可能带来新的隐私风险。正如我们所展示的，令人有些意外的是，当前的开源和专有视觉语言模型都是非常强大的图像地理定位器，这使得基于视觉语言模型的大规模地理定位成为一个迫在眉睫的隐私风险，而不仅仅是未来理论上的担忧。作为应对这一挑战的第一步，我们开发了一个新的基准测试 GPTGeoChat，用于测试视觉语言模型在与用户进行地理定位对话时进行内容审核的能力。我们收集了 1,000 组由内部标注人员与 GPT-4v 之间进行的图像地理定位对话，并对每一轮对话中泄露的位置信息粒度进行了标注。利用这一新数据集，我们评估了各种视觉语言模型通过判断何时泄露了过多位置信息来对 GPT-4v 地理定位对话进行审核的能力。我们发现，在识别国家或城市级别泄露的位置信息时，自定义微调模型与基于提示的 API 模型表现相当；然而，要准确审核更细粒度的信息（例如餐厅或建筑名称），似乎需要对监督数据进行微调。
英文摘要：
Vision Language Models (VLMs) are rapidly advancing in their capability to answer information-seeking questions. As these models are widely deployed in consumer applications, they could lead to new privacy risks due to emergent abilities to identify people in photos, geolocate images, etc. As we demonstrate, somewhat surprisingly, current open-source and proprietary VLMs are very capable image geolocators, making widespread geolocation with VLMs an immediate privacy risk, rather than merely a theoretical future concern. As a first step to address this challenge, we develop a new benchmark, GPTGeoChat, to test the ability of VLMs to moderate geolocation dialogues with users. We collect a set of 1,000 image geolocation conversations between in-house annotators and GPT-4v, which are annotated with the granularity of location information revealed at each turn. Using this new dataset, we evaluate the ability of various VLMs to moderate GPT-4v geolocation conversations by determining when too much location information has been revealed. We find that custom fine-tuned models perform on par with prompted API-based models when identifying leaked location information at the country or city level; however, fine-tuning on supervised data appears to be needed to accurately moderate finer granularities, such as the name of a restaurant or building.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
