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
ReFrame is a training‑free framework that enhances safety alignment for multimodal large language models at test time. It uses two lightweight agents: one generates risk and utility evidence, and the other rewrites prompts and routes images to create a safe proxy before invoking the deployed MLLM. Experiments show that ReFrame improves jailbreak defense, safety awareness, and reduces over‑sensitivity while maintaining multimodal utility.
By Wenzheng Jiang, Xuankun Rong, Yuanzhao Zhai, Dawei Feng, Huaimin Wang
The paper introduces Uni-SafeBench, a safety benchmark designed to evaluate the holistic safety of Unified Multimodal Large Models (UMLMs) across six safety categories and seven task types. It also presents Uni-Judger, a framework that separates contextual safety from intrinsic safety to enable rigorous assessment. Evaluations reveal that current unified models do not consistently maintain the safety alignment of their underlying language models, and open‑source UMLMs perform significantly worse on safety than specialized multimodal models, especially in generation tasks.
By Zixiang Peng, Yongxiu Xu, Qin-Yi Zhang, Jiexun Shen, Yi-Fan Zhang, Hongbo Xu, Yubin Wang, Gaopeng Gou
The paper examines how the tight integration of multimodal understanding and image generation in Unified Multimodal Models (UMMs) can create new safety vulnerabilities. It introduces RICE, an attack framework that exploits bidirectional interactions between generation and understanding to propagate unsafe signals across modalities. Experiments demonstrate high attack success rates in both Generation‑to‑Understanding and Understanding‑to‑Generation pathways, revealing previously overlooked safety weaknesses in UMMs.
By Kaishen Wang, Heng Huang
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:2608. 07535v1 Announce Type: cross Abstract: Multi-modal large language models (MLLMs) integrate heterogeneous modalities through modality alignment and fusion, enabling stronger understanding and reasoning.
By Xi Li, Shu Zhao, Xiaohan Zou, Fei Zhao, Fuxiao Liu, Yusen Zhang, Cheng Han, Yushun Dong, Jiaqi Wang
arXiv:2503. 11832v5 Announce Type: replace Abstract: Recent vision language models (VLMs) have made remarkable strides in generative modeling with multimodal inputs, particularly text and images.
By Yiwei Chen, Yuguang Yao, Yihua Zhang, Bingquan Shen, Gaowen Liu, Sijia Liu
arXiv:2609.20850v1 Announce Type: new
Abstract: While Multimodal Large Language Models (MLLMs) show remarkable advancements, their cross-modal capabilities introduce complex vulnerabilities that easi...
By Yueming Lyu, Yilian Shi, Haoxiang Tan, Linzhuang Zou, Qihao Wang, Guihua Yu, Jie Qin, Xin Gao, Chenyang Si, Jing Dong, Caifeng Shan
DiSCO is a zero‑shot, black‑box defense for text‑to‑image models that operates solely at the prompt level. It expands prompts with a distribution‑guided suffix using beam search and contrastive scoring against safe and unsafe image pools generated by the target model, iteratively refining until safe content is produced. The method improves safety on the I2P benchmark under various red‑teaming attacks, reducing attack success rates by 37.7% and 25.13% while preserving semantic fidelity and image coherence.
By Tong Zhang, Motasem Alfarra, Carlos Hinojosa, Christos Louizos, Bernard Ghanem
UReason is a benchmark that evaluates how well unified multimodal models (UMMs) align textual reasoning with image generation. It contains 2,000 human‑curated instances across five reasoning‑intensive tasks—Code, Arithmetic, Spatial, Attribute, and Text—and compares direct generation, reasoning‑guided generation, and decontextualized generation. The study finds that while reasoning‑guided generation improves over direct generation, decontextualized generation consistently outperforms it, indicating that the visual semantics in textual reasoning are not reliably reflected in the generated images.
By Cheng Yang, Chufan Shi, Bo Shui, Yaokang Wu, Muzi Tao, Huijuan Wang, Ivan Yee Lee, Yong Liu, Xuezhe Ma, Taylor Berg-Kirkpatrick
arXiv:2609.39688v1 Announce Type: cross
Abstract: Multimodal encoders such as CLIP underlie many downstream systems, but their web-scale training data embed harmful associations that safety alignment...
By Tobia Poppi, Silvia Cappelletti, Samuele Poppi, Marcella Cornia, Lorenzo Baraldi, Diego Garcia-Olano, Rita Cucchiara
arXiv:2606. 25034v2 Announce Type: replace-cross Abstract: General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI safety.
By Shikai Qiu, Xiaowen Xu, Benlei Cui, Ting Ma, Xiufeng Huang, Wenjing Jiang, Shaoxuan He, Haolei Xu, Chunyang Chai, Yujian Li, Yiliang Zhang, Guanghui Wang, Ziheng Wang, Ziwen Xu, Zhaoyu Fan, Jinhao Chen, Ruijie Jian, Hongxing Li, Chuxi Xiao, Xinyue Chen, Wenxuan Liu, Libin Dong, Yupeng Cao, Xiaoqian Xia, Jing Wang, Zhe Jiang, Zhenan Ye, Guang Yang, Bin Liu, Wei Peng, Ziqiang Zhu, Meihui Lian, Kaiwen Lv Kacuila, Haidong Ding, Dongjie Zhang, Yangfan Zhou, Bingyu Zhu, Yan Wang, Hai Zhao, Xuan Jin, Wei Zhao, Pengfei Sun, Huiming Zhang, Wei Wang, Xipeng Cao, Jialun Chen, Xiao Chen, Shaola Ren, Yunqing Hu, Bin Li, Chengwen Yao, Meng Huang, Xianfeng Li, Bin Tang, Chao Liu, Hui Xue, Longtao Huang, Haiwen Hong