Assessing the Geolocation Capabilities, Limitations and Societal Risks of Generative Vision-Language Models
This work addresses privacy concerns for users of social media and AI systems by systematically assessing the risks of unintended location inference from images.
The paper tackled the problem of evaluating the geolocation capabilities of generative vision-language models (VLMs) and found that they perform poorly on generic street-level images but achieve 61% accuracy on images resembling social media content, highlighting significant privacy risks.
Geo-localization is the task of identifying the location of an image using visual cues alone. It has beneficial applications, such as improving disaster response, enhancing navigation, and geography education. Recently, Vision-Language Models (VLMs) are increasingly demonstrating capabilities as accurate image geo-locators. This brings significant privacy risks, including those related to stalking and surveillance, considering the widespread uses of AI models and sharing of photos on social media. The precision of these models is likely to improve in the future. Despite these risks, there is little work on systematically evaluating the geolocation precision of Generative VLMs, their limits and potential for unintended inferences. To bridge this gap, we conduct a comprehensive assessment of the geolocation capabilities of 25 state-of-the-art VLMs on four benchmark image datasets captured in diverse environments. Our results offer insight into the internal reasoning of VLMs and highlight their strengths, limitations, and potential societal risks. Our findings indicate that current VLMs perform poorly on generic street-level images yet achieve notably high accuracy (61\%) on images resembling social media content, raising significant and urgent privacy concerns.