视觉语言模型下的地理位置信息细粒度隐私控制

Granular Privacy Control for Geolocation with Vision Language Models

July 6, 2024

作者: Ethan Mendes, Yang Chen, James Hays, Sauvik Das, Wei Xu, Alan Ritter

cs.AI

摘要

视觉语言模型（VLMs）在回答寻求信息的问题方面能力迅速提升。由于这些模型广泛部署在消费者应用中，它们可能会因为新兴的识别照片中的人物、对图像进行地理定位等能力而导致新的隐私风险。正如我们所展示的那样，令人惊讶的是，当前的开源和专有VLMs在图像地理定位方面非常有能力，使得利用VLMs进行广泛地理定位成为一种即时的隐私风险，而不仅仅是一个理论上的未来担忧。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VLMs在与用户进行地理定位对话方面的调节能力。我们收集了一组1,000个图像地理定位对话，这些对话是由内部标注者和GPT-4v之间进行的，并且标有每个回合中透露的位置信息的细粒度。利用这个新数据集，我们评估了各种VLMs在调节GPT-4v地理定位对话方面的能力，通过确定何时透露了过多的位置信息。我们发现，当识别泄霏的位置信息达到国家或城市级别时，定制的精细调整模型与提示的基于API的模型表现相当；然而，在准确调节更细粒度的信息，比如餐厅或建筑物的名称时，似乎需要在监督数据上进行定制调整。

English

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.