Chethan Krishnamurthy Ramanaik

On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspaces

This work proposes a white-box spectral-subspace-guided attack (SSGRA) that aligns intermediate representations with the subspace spanned by the bottom right singular vectors, offering a spectral interpretation of adversarial vulnerability in VLMs, providing insights for improving their robustness.