The paper investigates how Vision Language Models (VLMs) can be fooled by small, human‑imperceptible changes to images. It introduces a gradient‑based attack that targets only the vision encoder, reducing computational cost while still effectively disrupting both untargeted and targeted multimodal alignment. Experiments on open‑source VLMs such as Qwen2.5‑VL, Granite‑Vision, FastVLM, and Phi‑3.5‑Vision demonstrate that these perturbations can significantly alter the models’ textual outputs.
By Ilan Zini, Boussad Addad, Katarzyna Kapusta
The paper investigates how Vision Language Models (VLMs) can be fooled by tiny, human‑imperceptible changes to images. It introduces a gradient‑based attack that targets only the vision encoder, reducing computational cost while still effectively disrupting both untargeted and targeted multimodal interpretations. Experiments on open‑source VLMs such as Qwen2.5‑VL, Granite‑Vision, FastVLM, and Phi‑3.5‑Vision demonstrate that these small perturbations can dramatically alter the models’ textual outputs.
arXiv:2508. 08521v2 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) are increasingly being used in a broad range of applications, bringing their security and behavioral control to the forefront.
By Mansi Phute, Ravikumar Balakrishnan
The safety of large vision-language models is increasingly stress-tested by multimodal jailbreaks, yet existing attacks remain largely static at the meta level: template-based attacks freeze the image...
The paper introduces MemJack, a memory‑augmented multi‑agent framework that automatically generates jailbreak attacks on Vision‑Language Models (VLMs) using benign natural images as visual anchors. MemJack discovers visual anchors, camouflages them semantically, evaluates responses, repairs via reflection, and replans dynamically, forming a closed‑loop attack pipeline. The authors also create MemJack‑Bench, a dataset of over 113,000 interactive multimodal jailbreak trajectories, and show that MemJack achieves a 71.48% attack success rate against Qwen3‑VL‑Plus, reaching 90% under extended budgets, outperforming other baselines on natural‑image evaluation.
By Jianhao Chen, Haoyang Chen, Hanjie Zhao, Haozhe Liang, Zheng Wang, Tieyun Qian
The paper introduces Meta-Adaptive Multimodal Jailbreaking (MAMJ), a method that jointly optimizes an attack strategy prompt and attacker weights to generate more effective jailbreaks against vision‑language models. Using an LLM‑based critique to refine the strategy and group‑level success‑rate rewards to update the weights, MAMJ achieves high attack success rates on MM‑SafetyBench, outperforming existing baselines by up to 24.1 percentage points. The learned attacker also transfers to unseen models and remains robust against typical defenses, highlighting a systemic vulnerability in current VLMs.
By Benlei Cui, Shen Pang, Yuke Wang, Xuemei Dong, Yuwen Zhai, Jingqun Tang, Haiyang Yu, Hui Xue, Longtao Huang, Haiwen Hong
Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.
InfraPatch is a white‑box, per‑instance framework that generates small grayscale patches to target infrared‑adapted vision‑language models (IR‑VLMs). The method optimizes a single‑channel patch within a 5% local‑area budget, using proxy‑guided placement and task‑adaptive objectives to induce desired behaviors in image classification, captioning, and binary visual question answering. Across ten IR‑VLM variants tested on synthetic infrared images, InfraPatch achieves targeted attack success rates ranging from 86% to 100%, revealing significant vulnerability differences among architectures and tasks.
By Chengyin Hu, Dingyi Lu, Jiaju Han, Xiang Chen, Weiwen Shi, Jiahuan Long, Yiwei Wei, Jiujiang Guo
arXiv:2602.08136v2 Announce Type: replace-cross
Abstract: Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic...
By Md Rafi Ur Rashid, MD Sadik Hossain Shanto, Vishnu Asutosh Dasu, Shagufta Mehnaz
arXiv:2607. 11063v1 Announce Type: new Abstract: Despite progress in Embodied AI, Vision-and-Language Navigation systems remain vulnerable to adversarial visual disturbances.
By Chenyang Li, Kaige Li, Zeyu Jiang, Changhao Chen
arXiv:2608. 13453v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as generalist robotic policies capable of following diverse language instructions and performing a wide range of manipulation tasks.
By Yukun Dai, Mingzhe Dai, Tianshi Wang, Fengling Li, Jingjing Li, Lei Zhu
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