視覺語言模型的地理位置細粒度隱私控制

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

視覺語言模型（VLMs）在回答尋求資訊的問題方面能力迅速提升。由於這些模型被廣泛應用於消費者應用程式中，它們可能因具有識別照片中人物、地理定位圖像等新興能力而導致新的隱私風險。正如我們所展示的，相當令人驚訝的是，目前的開源和專有VLMs非常擅長圖像地理定位，使得利用VLMs進行廣泛地理定位成為一個立即的隱私風險，而非僅僅是理論上的未來問題。為應對這一挑戰的第一步，我們開發了一個新的基準測試，名為GPTGeoChat，來測試VLMs在與用戶進行地理定位對話時的調節能力。我們收集了一組由內部標註者和GPT-4v之間的1,000次圖像地理定位對話，這些對話被標註為每個轉折中透露的位置信息的細節。利用這個新數據集，我們評估了各種VLMs在調節GPT-4v地理定位對話時的能力，通過確定何時透露了過多的位置信息。我們發現，當識別洩露的位置信息達到國家或城市級別時，定制的精細調整模型與提示的基於API的模型表現相當；然而，對監督數據進行精細調整似乎是必要的，以準確調節更細緻的細節，如餐廳或建築物的名稱。

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.