MM-IFEval-Pro is a new multilingual benchmark for evaluating instruction-following in vision-language models, covering both Chinese and English tasks. It includes 4 major task categories, 24 subcategories, and 8 instruction categories with 52 subcategories, each sample featuring an average of 3.0 constraints to mimic complex instruction scenarios. A reinforcement-learning training set with Chinese and adversarial instructions improves model performance on MM-IFEval-Pro and transfers well to other multimodal benchmarks, showing strong cross-task and cross-language generalization.
By Changming Xiao, Zhenliang Ni, Jinhui He, Han Shu, Jie Hu
arXiv:2608. 10513v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) remain vulnerable to jailbreak attacks that exploit visual inputs to bypass safety alignment inherited from their language backbones.
By Caoyuan Ma, Wenpu Liu, Weichu Xie, Tian Gu, Shilei Zhao, Lingxi Min, Shuai Dong, Yuqi Xu, Ji Zhao, Ziyue Wang, Wenzheng Chang, Taiqiang Wu, Yongfu Zhu, Wenqi Shao, Yinqiang Zheng
arXiv:2607. 18958v1 Announce Type: cross Abstract: While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks.
By Sibo Wang, Jie Zhang, Shiguang Shan, Xilin Chen, Wen Gao
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.
Large vision-language models (LVLMs) remain vulnerable to jailbreak attacks that exploit visual inputs to bypass safety alignment inherited from their language backbones. We propose SafeCap, a reinforcement-learning framework that aligns LVLMs through learned self-captioning.
Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.
While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks. Existing defense methods predominantly target single-task scenarios (e.
The paper investigates how multimodal large language models are more susceptible to prompt injection when adversarial instructions are presented as text rather than as non-textual inputs like images. It proposes a training‑free defense that renders untrusted payloads into typographic images (or audio) before they reach the model, a method called Pictionary. Experiments on ten models and two benchmarks show that this approach significantly lowers attack success rates while maintaining normal functionality, and that fine‑tuning on image‑rendered instructions can further reduce the modality gap.
By Jie Zhang, Andrei Baroian, Jan N. van Rijn, Avital Shafran, Florian Tram\`{e}r
arXiv:2603.04364v2 Announce Type: replace-cross
Abstract: Multimodal web agents that process both screenshots and accessibility trees are increasingly deployed to interact with web interfaces, yet th...
By Haoyu Liu, Dingcheng Li, Lukas Rutishauser, Zeyu Zheng
Aligned vision‑language models (VLMs) are designed to combine grounded visual reasoning with safe generation. The study finds that when safety constraints are applied, these models often abstain from answering questions that they could answer under default instruction, yet visual evidence continues to influence the decoding process. The authors show that safety‑induced abstention alters late‑stage hidden‑state dynamics, and that targeted interventions can restore grounded answering without retraining or changing visual inputs.
arXiv:2610.33841v1 Announce Type: cross
Abstract: When an image and its caption disagree, can a user reliably control which one a vision-language model (VLM) follows? Accuracy alone cannot answer thi...
By Maxime Dassen, Alexander Martin, Andrew Yates, Reno Kriz, William Walden
arXiv:2606. 31876v1 Announce Type: new Abstract: To improve safety in Large Language Models (LLMs) we can either perform post-training alignment or exploit refusal directions in the activation space.
By Moreno D'Inc\`a, Massimiliano Mancini, Nicu Sebe