GeoDetect: Geometric Adversarial Detection for Vision-Language Pre-trained Models

Jul 17, 2026

Researchers have introduced GeoDetect, a method that utilizes the geometric properties of embedding spaces in vision-language pre-trained models (VLPs) to detect adversarial examples. By analyzing the anisotropic structure of VLP embeddings, they found that adversarial examples tend to have greater distances to random points compared to clean examples. GeoDetect leverages this property to reliably identify adversarial attacks across various VLP architectures and threat scenarios, including both unimodal and multimodal attacks.

Why it matters: This work offers a robust and practical approach to detecting adversarial attacks in vision-language models, enhancing their safety and reliability.

Full story at: arXiv Computer Vision ↗