The paper introduces SAFE-PRO, a method for enhancing safety in multimodal large language models by proactively asking clarifying questions when cross‑modal ambiguity poses intent‑level risks. SAFE‑PRO employs a Risk‑Conditioned Uncertainty signal that blends predictive entropy with a learned cross‑modal risk score to guide both question‑asking and path optimization, prioritizing safety while reducing over‑refusal. The authors also present the SSUI‑Dialog dataset and demonstrate that SAFE‑PRO outperforms existing approaches, including GPT‑4o and Claude‑3.5‑Sonnet, across multiple benchmarks.
By Wei Cai, Jian Zhao, Yuchen Yuan, Xuelong Li
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 the concept of compositional unalignment to audit safety in large vision‑language models (LVLMs). It shows that minimal fine‑tuning can match reinforcement‑learning benchmarks, yet recognition and refusal of compositional harm are decoupled, revealing fragility in safety mechanisms. The authors propose CMaG, a training‑free method that uses a refusal‑versus‑compliance log‑probability margin to identify cross‑modal interactions, and demonstrate that a single backward pass can significantly reduce safety scores while preserving coherence.
By Hong kyu Lee, Kai Shu, Li Xiong
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
Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the safety surface: risks can arise from multimodal question answering, assistant responses, and cross-modal composition, while moderation policies may vary across products, regions, and deployment stages.
Multimodal large language models (MLLMs) can act unsafely when individually benign images and texts are interpreted jointly. Beyond implicit reasoning risk, where reasoning drifts toward harm, we iden...
The paper introduces a counterfactually anchored evidence attribution approach for multi‑turn large language model safety failures. It presents a new dataset of 1,762 conversations, including adversarial, benign twins, and high‑risk vocabulary variants, and trains a lightweight hierarchical model that accurately predicts safety violations and attributes them to specific user turns and token spans. The model achieves high detection performance (F1 = 0.988) and significantly reduces adversarial confidence when top‑attributed tokens are removed, while maintaining low false‑positive rates on benign conversations.
By Srinivasan Subramanian, Kazi Aminul Islam, Md. Abdullah Al Hafiz Khan
SaFeR-Steer is a progressive multi‑turn alignment framework that uses staged synthetic bootstrapping and tutor‑in‑the‑loop GRPO to train a single student model against adaptive, on‑policy attacks. It introduces Trajectory‑Consistent Summative Reward (TCSR) to ensure that low‑quality turns impact the overall trajectory reward. The authors release the STEER dataset and demonstrate that SaFeR‑Steer significantly improves safety and helpfulness on both single‑turn and multi‑turn benchmarks for Qwen2.5‑VL models.
By Haolong Hu, Hanyu Li, Tiancheng He, Huahui Yi, An Zhang, Qiankun Li, Kun Wang, Yang Liu, Zhigang Zeng
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:2512. 20806v3 Announce Type: replace Abstract: Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment.
By Anselm Paulus, Ilia Kulikov, Brandon Amos, R\'emi Munos, Ivan Evtimov, Kamalika Chaudhuri, Arman Zharmagambetov
arXiv:2512. 05518v2 Announce Type: replace-cross Abstract: Open-source Large Language Models (LLMs) play a critical role in the democratization of AI, yet their "open" nature introduces more avenues for malicious actors to misuse them for harmful purposes.
By Jason Vega, Gagandeep Singh
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