arXiv AI August 11, 2026 By Xi Li, Shu Zhao, Xiaohan Zou, Fei Zhao, Fuxiao Liu, Yusen Zhang, Cheng Han, Yushun Dong, Jiaqi Wang

Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards

Read the original on arXiv AI →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Aug 10

CASA: Classification Augmented with Safety Attention for Robust Multimodal Alignment

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

llms reinforcement-learning fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jul 14

Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs

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

llms fine-tuning multimodal safety

arXiv AI

23h ago

COMIC: Reference-Aware Safety Gating for Multimodal Large Language Models

arXiv:2608. 17234v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are increasingly used to interact with screenshots, scanned documents, diagrams, and other visually grounded inputs.

By Md Abdullahil Oaphy, Anhao Xiang, Zongxing Xie, Huayue Gu, Chenyu Wang, Honghui Xu

llms computer-vision multimodal benchmarks safety

arXiv AI

Jun 2

Jailbreaking Multimodal Large Language Models using Multi-Clip Video

arXiv:2606. 02111v1 Announce Type: cross Abstract: As multimodal large language models (MLLMs) have advanced to process video inputs, concerns have emerged about their potential for malicious misuse.

By Choongwon Kang, Seungjong Sun, Hyunmin Jun, Jang Hyun Kim

llms multimodal safety

arXiv AI

Jun 29

Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety

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

llms fine-tuning multimodal benchmarks safety

arXiv AI

23h ago

Does Unification Come at a Cost? Uni-SafeBench: A Safety Benchmark for Unified Multimodal Large Models

arXiv:2604. 00547v2 Announce Type: replace Abstract: Unified Multimodal Large Models (UMLMs) integrate understanding and generation capabilities within a single architecture.

By Zixiang Peng, Yongxiu Xu, Qin-Yi Zhang, Jiexun Shen, Yi-Fan Zhang, Hongbo Xu, Yubin Wang, Gaopeng Gou

llms multimodal benchmarks safety

Related stories

CASA: Classification Augmented with Safety Attention for Robust Multimodal Alignment

Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs

COMIC: Reference-Aware Safety Gating for Multimodal Large Language Models

Jailbreaking Multimodal Large Language Models using Multi-Clip Video

Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety

Does Unification Come at a Cost? Uni-SafeBench: A Safety Benchmark for Unified Multimodal Large Models