arXiv AI July 9, 2026 By Chethan Krishnamurthy Ramanaik, Tobias Callies, Michael Hecht, Eirini Ntoutsi

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

arXiv:2607. 07375v1 Announce Type: cross Abstract: 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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 24

PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models

arXiv:2606. 24388v1 Announce Type: new Abstract: We introduce a large-scale, open-source dataset of pre-generated adversarial attacks for vision-language models (VLMs).

By Simone Gallivanone, Hossein Khodadadi, Mauro Dore, Mauro Medda, Nicola Franco

llms fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jun 4

Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms

arXiv:2606. 04767v1 Announce Type: new Abstract: The robustness of deep neural networks is crucial for safety-critical deployments, yet existing evaluation methods are often attack-dependent and lack interpretability.

By Chong Zhang, Xiang Li, Jia Wang, Qiufeng Wang, Xiaobo Jin

llms safety

arXiv AI

Jun 18

Revealing Hidden Vulnerabilities in Autoencoders through Gradient Signal Restoration

arXiv:2505. 03646v5 Announce Type: replace-cross Abstract: 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.

By Chethan Krishnamurthy Ramanaik, Arjun Roy, Tobias Callies, Eirini Ntoutsi

multimodal safety

arXiv Machine Learning

Jul 17

GeoDetect: Geometric Adversarial Detection for VLPs

arXiv:2607. 14737v1 Announce Type: cross Abstract: Vision-language pre-trained models (VLPs) are widely used in real-world applications.

By Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie, James Bailey, Sarah Erfani

rag multimodal safety

arXiv AI

Jun 10

Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction

arXiv:2606. 10571v1 Announce Type: cross Abstract: Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness.

By Lijia Yu, Jiuxin Cao, Yuchen Qiang, Changhao Chen, Yifei Huang, Bo Liu

llms multimodal safety

arXiv AI

Jun 11

Diffusion-based Cumulative Adversarial Purification for Vision Language Models

arXiv:2506. 03933v2 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to adversarial perturbations poses a significant threat to their reliability in real-world applications.

By Jia Fu, Yongtao Wu, Yihang Chen, Kunyu Peng, Xiao Zhang, Volkan Cevher, Sepideh Pashami, Anders Holst

llms rag diffusion multimodal safety

Related stories

PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models

Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms

Revealing Hidden Vulnerabilities in Autoencoders through Gradient Signal Restoration

GeoDetect: Geometric Adversarial Detection for VLPs

Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction

Diffusion-based Cumulative Adversarial Purification for Vision Language Models