GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations

TL;DR

GeoShield is a novel adversarial framework that effectively protects user geolocation privacy from vision-language models by generating minimal, scale-adaptive perturbations that are robust across image resolutions.

Contribution

This work introduces GeoShield, the first adversarial approach specifically designed to defend against geolocation inference by advanced vision-language models in real-world scenarios.

Findings

GeoShield outperforms prior methods in black-box settings.

It achieves strong privacy protection with minimal visual impact.

The framework is effective across various image resolutions.

Abstract

Vision-Language Models (VLMs) such as GPT-4o now demonstrate a remarkable ability to infer users' locations from public shared images, posing a substantial risk to geoprivacy. Although adversarial perturbations offer a potential defense, current methods are ill-suited for this scenario: they often perform poorly on high-resolution images and low perturbation budgets, and may introduce irrelevant semantic content. To address these limitations, we propose GeoShield, a novel adversarial framework designed for robust geoprivacy protection in real-world scenarios. GeoShield comprises three key modules: a feature disentanglement module that separates geographical and non-geographical information, an exposure element identification module that pinpoints geo-revealing regions within an image, and a scale-adaptive enhancement module that jointly optimizes perturbations at both global and local levels to ensure effectiveness across resolutions. Extensive experiments on challenging benchmarks show that GeoShield consistently surpasses prior methods in black-box settings, achieving strong privacy protection with minimal impact on visual or semantic quality. To our knowledge, this work is the first to explore adversarial perturbations for defending against geolocation inference by advanced VLMs, providing a practical and effective solution to escalating privacy concerns.