MLLM Safety

MLLM: Multimodal Large Language Model

Follow this topic Ask about this topic

Latest papers

27 papers6 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Defending Against Dormant Poisoning Attacks Across Language and Multimodal Agents
Oct 17, 2026Wonjun Lee, Vaidehi Patil, Zaid Khan +4AI Agent Safety Backdoor Defense in LLMs
When Reasoning Is Not Enough: Proactive Inquiry for Cross-Modal Safety in Multimodal Large Language Models
Oct 15, 2026Wei Cai, Jian Zhao, Yuchen Yuan +1Multimodal Multi-Turn Safety Alignment VLM Safety
Institute of Artificial Intelligence (TeleAI), China Telecom, P. R. China. · Peking University. · School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an 710072, P. R. China.
Scenes as an Attack Surface: Uncovering Scene-Grounded Safety Failures in MLLMs
Oct 8, 2026Tongxi Wu, Yuyang Cheng, Jiacheng Xian +5MLLM Safety Adversarial Attacks on VLMs
Nanjing University · The Hong Kong University of Science and Technology (Guangzhou) · Independent Researcher +2
Reading, Not Manipulating: Leveraging Router Logits for Multimodal Safety in MoE Vision-Language Models
Oct 6, 2026Ziyuan Yang, Wenxuan Ding, Shangbin Feng +1Vision-Language Models Safety Filtering
University of Washington · New York University
MLLMs Fail to Refuse when Using Tools Agentically
Oct 2, 2026Rikiya Takehi, Ryo Hachiuma, Shaona Ghosh +3MLLM Safety LLM Agent Safety
MIT · NVIDIA
ThinkingGuard: Decoding Implicit Hazards via Step-by-Step Risk Attribution in Multimodal Large Language Models
Sep 29, 2026Ruochen Zhang, Yao Huang, Yitong Sun +5Multimodal Reasoning LLM Safety
Beihang University Beijing, China · Tsinghua University Beijing, China · Institute of Artificial Intelligence Beihang University Beijing, China State Key Laboratory of AI Safety
Nemotron 3.5 Content Safety Moderator: A Compact Multimodal, Multilingual, and Reasoning Enabled Content Safety Moderator
Aug 27, 2026Varun Singh, Anuj Doshi, Makesh Narsimhan Sreedhar +2Multimodal Content Moderation LLM Guardrails
NVIDIA Santa Clara, CA
ReFrame: Evidence-Guided Test-Time Safety Alignment in Multimodal Large Language Models
Aug 21, 2026Wenzheng Jiang, Xuankun Rong, Yuanzhao Zhai +2MLLM Safety LLM Safety Alignment
College of Computer Science and Technology, National University of Defense Technology · State Key Laboratory of Complex & Critical Software Environment · School of Computer Science, Wuhan University
COMIC: Reference-Aware Safety Gating for Multimodal Large Language Models
Aug 18, 2026Md Abdullahil Oaphy, Anhao Xiang, Zongxing Xie +3MLLM Safety LLM Safety
Kennesaw State University, Kennesaw, GA, USA
Exploring and Bridging Knowledge Holes in Unlearned Multimodal Large Language Models
Aug 3, 2026Junxiang You, Junkai Chen, Yuhao He +3Multimodal Large Language Models MLLM Unlearning
University of Chinese Academy of Sciences · Institute of Automation, Chinese Academy of Sciences · 3Cloudspace Technology
Shieldstral
Jul 28, 2026Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli +273Language Model Safety Evaluation Content Moderation
Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards
Jul 27, 2026Xi Li, Shu Zhao, Xiaohan Zou +6MLLM Safety Adversarial Attacks on VLMs
University of Alabama at Birmingham · NVIDIA · Penn State University +4
Harnessing Textual Refusal Directions for Multimodal Safety
Jun 30, 2026Moreno D'Incà, Nicu Sebe, Massimiliano ManciniLanguage Model Safety Evaluation Multimodal Large Language Models
University of Trento
SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning
Jun 22, 2026SingGuard TeamLanguage Model Safety Evaluation LLM Guardrails
1AI Security Lab, Ant Group
Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs
Jun 20, 2026Jiayi Li, Kun ZhanRefusal Behavior in Language Models LLM Guardrails
Lanzhou University
Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models
Jun 2, 2026Hashmat Shadab Malik, Muzammal Naseer, Salman KhanMLLM Safety Multilingual Language Model Evaluation
Mohamed Bin Zayed University of AI, UAE · Khalifa University, UAE · Australian National University, Australia
Investigating and Alleviating Harm Amplification in LLM Interactions
Jun 1, 2026Ruohao Guo, Wei Xu, Alan RitterMLLM Safety Language Model Safety Evaluation
Georgia Institute of Technology
GuardAD: Safeguarding Autonomous Driving MLLMs via Markovian Safety Logic
May 11, 2026Tianyuan Zhang, Peng Yue, Zihao Peng +8MLLM Safety Autonomous Driving
Beihang University · Zhongguancun Laboratory · Peking University
SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
Apr 21, 2026Josue Torres-Fonseca, Naihao Deng, Yinpei Dai +5Safety Evaluation of VLA Models LLM Safety Benchmarks
University of Michigan · Boise State University
Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs
Apr 10, 2026Jinqi Luo, Jinyu Yang, Tal Neiman +5MLLM Safety Multimodal Large Language Models
University of Pennsylvania · Amazon · University of Central Florida
CASA: Classification Augmented with Safety Attention for Robust Multimodal Alignment
Mar 31, 2026Anurag Kumar, Raghuveer Peri, Jon Burnsky +4MLLM Safety LLM Safety Alignment
The Ohio State University · AWS
When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm
Mar 25, 2026Ye Leng, Junjie Chu, Mingjie Li +5MLLM Safety Image Generation
CISPA Helmholtz Center for Information Security · Xi’an Jiaotong University · Flexera
Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models
Mar 23, 2026Rui Yang Tan, Yujia Hu, Roy Ka-Wei LeeMLLM Safety Adversarial Attacks on VLMs
Singapore University of Technology and Design. · University of British Colombia.
OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences
Mar 10, 2026Ming Wen, Kun Yang, Jingyu Zhang +4MLLM Safety LLM Safety
Fudan University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China · Ant Group, Hangzhou, China +1
SaFeR-ToolKit: Structured Reasoning via Virtual Tool Calling for Multimodal Safety
Mar 3, 2026Zixuan Xu, Tiancheng He, Huahui Yi +7Cultural Safety Evaluation of VLMs VLM Safety
Huazhong University of Science and Technology · Beijing University of Posts and Telecommunications · West China Hospital, Sichuan University +1
MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models
Mar 3, 2026Zhongxi Wang, Yueqian Lin, Jingyang Zhang +3Multimodal Large Language Models Multi-Turn Jailbreak Attacks
1Duke University · 2Virtue AI
Towards Multi-modal Multi-turn Safety: From Agentic Interaction to Strategic Alignment
Jan 8, 2026Han Zhu, Jiale Chen, Chengkun Cai +8Language Model Safety Evaluation Multimodal Large Language Models
Hong Kong University of Science and Technology · University College London · AISpeech +1
SGM: Safety Glasses for Multimodal Large Language Models via Neuron-Level Detoxification
Dec 17, 2025Hongbo Wang, AprilPyone MaungMaung, Isao EchizenMLLM Safety Multimodal Robustness
1Graduate School of Information Science and Technology, The University of Tokyo, Japan · 2Information and Society Research Division, National Institute of Informatics, Japan · 3The Graduate University for Advanced Studies, SOKENDAI, Japan

Oct 17, 2026J/K move · Enter open · S save

Defending Against Dormant Poisoning Attacks Across Language and Multimodal Agents

Wonjun Lee, Vaidehi Patil, Zaid Khan, Yue Zhang+3

AI Agent Safety Backdoor Defense in LLMs Backdoor Attacks Safety-Preserving Fine-Tuning of Language Models MLLM Safety

Open paper AskPDF arXiv

Recent work shows that attackers can implant dormant malicious behaviors that remain hidden at release but emerge after benign fine-tuning. As foundation models are used as agents, whether dormant poisoning extends to harmful agent actions and multimodal settings remains unclear. We show two agentic risks: (1) harmful behaviors activated by benign fine-tuning can extend to unseen actions; (2) multiple harmful behaviors can coexist and be jointly activated by benign downstream fine-tuning. Existing defenses often rely on external safe responses, which are hard to obtain for agent actions, or a trusted clean reference model. We exploit a key property of dormant poisoning: the attacker must preserve safe behavior at release to conceal poisoning, and this behavior can serve as a safety reference. Leveraging this property, we automatically construct a Safety Buffer pairing harmful inputs with the released model's responses and benign versions generated by the same model to remove harmful intent. The Safety Buffer can replace external safe responses in existing defenses, but these defenses do not distinguish updates that weaken safety from those that preserve it, often increasing over-refusal or reducing utility. To address this limitation, we introduce LookAhead Defense, which previews benign fine-tuning updates using the Safety Buffer and penalizes only updates predicted to weaken safe behavior on harmful inputs or increase the likelihood of refusals on benign versions in the Safety Buffer. Across language models, language agents, and multimodal agents, LookAhead Defense reduces harmful behavior in agents from up to 93.9% to at most 14.2% and harmful responses in language models from up to 92.5% to at most 2.0% versus vanilla fine-tuning, while maintaining competitive utility and low over-refusal. It remains effective against other poisoning methods.