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 paper introduces an end‑to‑end framework for testing image‑triggered command injection on computer‑use agents (CUAs). It demonstrates that a local visual patch can cause verifiable environmental effects through the entire pipeline—from screenshot input, through vision‑language‑model generation, action parsing, to execution—by training and deploying patches on GitHub Pages and a CSDN clone. Across five open‑source or publicly available GUI‑agent or VLM backends, the study reports 84.5% T‑ASR, 47.0% TAPR, and 20.3% E2E‑ASR success rates, with trajectory analysis revealing that some attacks first execute malicious terminal commands before continuing the original task.
By Zhihao Liu, Hongyu Sun, Zhiyuan Fu, Xiaonan Duan, Jice Wang, Shangru Zhao, Weizhi Meng, Wuxin Yang, Yangfan Zhou, Yuqing Zhang
The paper introduces MPS-Bench, a benchmark of 5,181 scenarios from 584 real-world images across 12 high-risk domains, each paired with a hidden user profile, to evaluate personalized safety in vision‑language models (VLMs). Eight leading VLMs were tested and found to almost always respond directly (86‑99%) without seeking missing context, scoring no higher than 2.6/5 on personalized safety. The authors identify a phenomenon called visual dominance, where visual information enters text representations early and suppresses textual risk signals, and propose PRISM, a lightweight input monitor that predicts when a query should be deferred, achieving 0.978 AUC and outperforming all tested models on the safety‑utility Pareto frontier.
By Edward Sun, Yuchen Wu, Zixian Ma, Eric Hanchen Jiang, Yijia Xiao, Xiaoyuan Yi, Ranjay Krishna, Wei Wang, Jindong Wang, Aylin Caliskan
arXiv:2607. 00218v1 Announce Type: cross Abstract: Vision-language models (VLMs) are now proposed as runtime safety guards for embodied agents in homes and factories.
By Siddhant Panpatil, Arth Singh, Mijin Koo, Chaeyun Kim, Haon Park, Dasol Choi
The paper introduces COMIC, a reference‑aware safety gate designed for multimodal large language models (MLLMs). COMIC detects the operation requested by a user, identifies visual targets through OCR and open‑vocabulary proposals, and evaluates safety on explicit operation‑target pairs, using max‑risk aggregation and quality‑aware routing to decide whether to allow or block a request. Experiments on several open‑source MLLMs and jailbreak benchmarks show that COMIC improves robustness while maintaining benign utility and efficiency.
By Md Abdullahil Oaphy, Anhao Xiang, Zongxing Xie, Huayue Gu, Chenyu Wang, Honghui Xu
arXiv:2607. 11818v1 Announce Type: cross Abstract: We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents.
By Kaixin Ma, Di Feng, Alexander Metz, Jiarui Lu, Eshan Verma, Afshin Dehghan