Tobias Callies | Searcharxiv

arXiv2026

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

Adversarial vulnerability in deep neural networks (DNNs) has been studied from the perspectives of decision-boundary geometry, feature robustness, input-output Jacobians, and the instability of inverse problems. Here, we focus on the spectral structure of intermediate linear transformations that propagate information through modern DNNs, an unexplored mechanism of adversarial vulnerability. Specifically, we investigate transformer-based vision-language models, whose linear layers admit interpretable spectral decompositions and whose widespread adoption makes understanding their robustness increasingly important. We propose a white-box spectral-subspace-guided attack (SSGRA) that aligns intermediate representations with the subspace spanned by the bottom right singular vectors. Our experiments show improved attack effectiveness over existing baselines. In addition, SSGRA offers a spectral interpretation of adversarial vulnerability in VLMs, providing insights for improving their robustness.

cs.LG↗

arXiv2025

Revealing Hidden Vulnerabilities in Autoencoders through Gradient Signal Restoration

Adversarial robustness of deep autoencoders (AEs) has received less attention than that of discriminative models, although their compressed latent representations induce ill-conditioned mappings that can amplify small input perturbations and destabilize reconstructions. Existing white-box attacks for AEs, which optimize norm-bounded adversarial perturbations to maximize reconstruction damage, often converge to suboptimal perturbations, thereby potentially overstating AE robustness. We show that this limitation is linked to vanishing adversarial loss gradients during backpropagation through ill-conditioned layers, associated with near-zero singular values in their intermediate weight matrices. To address this, we propose GRILL (Gradient Signal Restoration in Ill-Conditioned Layers), a framework designed to mitigate gradient degradation and improve the reliability of adversarial robustness evaluation in encoder-decoder architectures. GRILL is designed to mitigate adversarial gradient degradation during optimization, enabling attacks to better approximate high-distortion perturbations under fixed norm constraints. Through extensive experiments across multiple AE architectures, under both sample-specific and universal attacks, as well as standard and adaptive attack settings, we show that GRILL significantly increases attack effectiveness, thereby exposing vulnerabilities hidden by existing attack limitations. Beyond AEs, we provide preliminary evidence that modern multimodal encoder-decoder architectures exhibit similar vulnerabilities.

cs.LG↗