Granular Privacy Control for Geolocation with Vision Language Models

TL;DR

This paper highlights the privacy risks posed by vision language models' ability to geolocate images and introduces GPTGeoChat, a benchmark dataset, to evaluate and improve models' capacity to moderate geolocation information disclosure.

Contribution

The paper presents GPTGeoChat, a new benchmark dataset for testing VLMs' ability to moderate geolocation dialogue disclosures, and evaluates various models' effectiveness in privacy control.

Findings

Fine-tuned models match API-based models at country/city level geolocation detection.

Supervised fine-tuning improves moderation of fine-grained location details.

Widespread geolocation ability of VLMs poses immediate privacy risks.

Abstract

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.