arXiv Machine Learning July 2, 2026 By Kai Hu, Akash Bharadwaj, Weichen Yu, Matt Fredrikson

Steal the Patch Size: Adversarially Manipulate Vision-Language Models

Read the original on arXiv Machine Learning →

arXiv:2607. 00174v1 Announce Type: cross Abstract: We present a black-box model-stealing attack that recovers private vision-tokenizer configurations of deployed vision-language models (VLMs), including the visual patch size and input preprocessing pipeline.

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

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

arXiv Machine Learning

Jun 11

Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations

arXiv:2605. 16651v2 Announce Type: replace-cross Abstract: Explanation mechanisms are increasingly used to support transparency and trust in vision-language models (VLMs), particularly in settings where model decisions require human oversight.

By Narges Babadi, Hadis Karimipour

llms multimodal safety

arXiv Machine Learning

Jun 30

High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models

arXiv:2512. 21815v4 Announce Type: replace-cross Abstract: Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks.

By Mengqi He, Xinyu Tian, Xin Shen, Jinhong Ni, Shu Zou, Zhaoyuan Yang, Jing Zhang

llms multimodal safety

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 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

Jul 7

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models

arXiv:2607. 02819v1 Announce Type: cross Abstract: Cloud-edge Large Vision-Language Model (LVLM) inference enables efficient deployment by splitting computation between edge devices and cloud servers.

By Zikai Zhang, Rui Hu, Olivera Kotevska, Jiahao Xu

llms robotics multimodal benchmarks

Related stories

Diffusion-based Cumulative Adversarial Purification for Vision Language Models

Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations

High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models

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

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

Vision Token Manipulation Attacks on Cloud-Edge Inference of Large Vision-Language Models