T-VSS: Test-Time Visual Subspace Steering for Adversarial Robustness of Vision-Language Models

Jaehyuk Jang, Minseok Seo, Minseok Seo. Seungju Cho +3

Vision-language models (VLMs) achieve strong zero-shot recognition, but they remain highly vulnerable to adversarial perturbations. Recent test-time adaptations improve robustness…