SafeAtlas-VL introduces a large multimodal safety dataset with 1.5 million instances, rating image, request, and response risks on a five‑level ordinal scale across 15 harm categories and 55 subcategories. The accompanying SafeAtlas‑Bench provides 5,000 held‑out cases for evaluating ordinal predictions and continuous risk scores. Models trained on this data, including an 8B Guard model, achieve state‑of‑the‑art performance, outperforming prior benchmarks by about 4% in F1 score.
By Zongrui Wang, Xiangyang Zhu, Sicheng Wang, Han Wang, Dingyi Rong, Zeyu Zhang, Chunyi Li, Yue Shi, Kaiwei Zhang, Zicheng Zhang, Yuan Tian, Qi Jia, Yan Teng, Wei Sun, Ning Liu, Guangtao Zhai
arXiv:2609.36562v1 Announce Type: cross
Abstract: While Multimodal Large Language Models (MLLMs) are increasingly deployed in safety-critical domains, their reliability is threatened by multimodal im...
By Ruochen Zhang, Yao Huang, Yitong Sun, Jiahe Xie, Jin Yan, Jifan Ma, Yuanfang Guo, Xingxing Wei
arXiv:2607. 09697v1 Announce Type: new Abstract: Existing safety mechanisms for multimodal large language models (MLLMs) face a fundamental trade-off between safety and utility.
By Jiayi Li, Kun Zhan
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
arXiv:2609.22094v1 Announce Type: cross
Abstract: Content moderation systems traditionally entangle multimodal understanding with policy-specific classification, requiring full pipeline retraining fo...
By Zeeshan Ahmed, Yang Qin, Hanqing Huang
arXiv:2604. 00310v2 Announce Type: replace-cross Abstract: Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions.
By Anurag Kumar, Raghuveer Peri, Jon Burnsky, Alexandru Nelus, Rohit Paturi, Srikanth Vishnubhotla, Yanjun Qi
The paper introduces COLAGUARD, a guardrail model that embeds multi-step safety reasoning into a continuous latent space, allowing efficient hidden-state propagation during inference. Compared to existing methods, COLAGUARD achieves an 8.24‑point macro‑F1 improvement over Llama Guard 3 and matches the explicit reasoning baseline GuardReasoner, while delivering a 12.9× speedup and a 22.4× reduction in token usage across ten moderation settings and eight safety benchmarks.
By Siddharth Sai, Xiaofei Wen, Muhao Chen
The paper introduces MINT‑Safe, a new open‑source dataset of 11,270 multi‑image dialogues and 500 refusal VQA pairs designed to expose safety risks in multi‑modal large language models during open‑ended conversations. It also proposes TAD‑Align, a turn‑aware dual‑objective reward framework that dynamically up‑weights dialogue turns with inconsistent safety behavior, improving safety metrics on Qwen2.5‑VL‑7B‑Instruct and LLaVA‑Next‑7B. The results show over 10% reduction in attack success rate and notable gains in harmlessness and helpfulness while maintaining overall model performance.
By Han Zhu, Jiale Chen, Chengkun Cai, Shengjie Sun, Haoran Li, Yujin Zhou, Chi-Min Chan, Pengcheng Wen, Lei Li, Yike Guo, Sirui Han
arXiv:2606. 29887v1 Announce Type: new Abstract: In real-world applications, guardrails are often expected to identify unsafe user-model interactions according to application-specific safety policies, rather than relying on predefined risk taxonomies.
By Jiacheng Zhang, Haoyu He, Sen Zhang, Shen Wang, Xiaolei Xu, Yuhao Sun, Meng Shen, Feng Liu
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
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: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