GeoDetect: Geometric Adversarial Detection for VLPs

TL;DR - GeoDetect is a method for detecting adversarial examples against vision-language pre-trained models (VLPs) by exploiting geometric properties of their embedding spaces, addressing a gap where prior detection work focused on single-modality models.

• Analyzes VLP embedding geometry and finds structured anisotropy distinct from unimodal vision models.
• Provides theoretical analysis showing adversarial examples get pushed off-manifold, increasing their expected geometric distance to randomly sampled points versus clean inputs.
• Proposes GeoDetect, which uses geometric scores capturing these off-manifold deviations to flag adversarial examples.
• Reports reliable detection across diverse VLP architectures and threat settings, including unimodal, multimodal, and adaptive attacks (specific metrics not provided in the abstract).