MLLM Safety

MLLM: Multimodal Large Language Model

Follow this topic Ask about this topic

Latest papers

36 papers9 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

TraceRouter++: Causal Semantic Routing Realignment via Optimal Transport
Nov 3, 2026Chuancheng Shi, Shangze Li, Wenhua Wu +5LLM Safety LLM Safety Alignment
The University of Sydney · Nanjing University of Science and Technology · National University of Singapore +1
PGuard: A Native, Streaming, and Plug-in Guardrail for Multimodal Large Language Models
Nov 2, 2026Junyu Lin, Mengjie Wu, Yonghao Dong +11LLM Guardrails LLM Safety Monitoring
Alibaba AAIG
What Does a Safety Label Measure? Auditing Situational-Safety Benchmarks for Multimodal LLMs
Oct 31, 2026Wayner Barrios, Kenneth BarriosLLM Safety Benchmarks MLLM Safety
Wiqonn · Technical AI Safety Project course of BlueDot Impact
Erase the Injected Region: Multimodal Prompt-Injection Defense with On-Policy Self-Distillation
Oct 30, 2026Shuo Hong, Jiaxin Ma, Xidi Cai +1Prompt Injection Defense MLLM Safety
South China University of Technology
LLM Detoxification via Transition-Aware Reward-Guided Representation Sampling
Oct 30, 2026Aishan Liu, Yisong Xiao, Xianglong Liu +7LLM Safety Activation Steering
SKLCCSE, the School of Computer Science and Engineering, Beihang University, Beijing 100191, China. · BAAI, Beijing 100191, China. · the College of Computing & Data Science, Nanyang Technological University, Singapore 639798. +1
Omni-UBench: Benchmarking Omni-Modal LLM-based Guardrails Across Safety, Utility, and Reliability
Oct 22, 2026Junhao Wang, Yidou Chen, Li Lu +6LLM Safety Benchmarks MLLM Safety
State Key Laboratory of Blockchain and Data Security, Zhejiang University · Alibaba Group
MPIDetector: Detecting Multi-modal Prompt Injection via LLM-based Reasoning
Oct 21, 2026Yiheng Li, Jingyue LiPrompt Injection Detection MLLM Safety
Paul G. Allen School of Computer Science & Engineering University of Washington Seattle, WA, USA · Department of Computer Science Norwegian University of Science and Technology Trondheim, Norway
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
UNC Chapel Hill · Kyung Hee University
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
Unified Hallucination Fuzzing for Multimodal Large Language Models
Jul 15, 2026Pengfei Zhou, Jiajun Song, Zhiwei Tang +11Hallucination in Language Models Multimodal Hallucination
National University of Singapore · DAMO Academy, Alibaba Group · Renmin University of China +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

Nov 3, 2026J/K move · Enter open · S save

TraceRouter++: Causal Semantic Routing Realignment via Optimal Transport

Chuancheng Shi, Shangze Li, Wenhua Wu, Hengzhi Chen+4

The University of Sydney · Nanjing University of Science and Technology · National University of Singapore+1

LLM Safety LLM Safety Alignment Adversarial Robustness of Language Models Causal Interventions in Language Models MLLM Safety

Open paper AskPDF arXiv

Despite their remarkable capabilities, large foundation models (LFMs) remain susceptible to adversarial manipulation. Current safety intervention methods primarily rely on the locality hypothesis, rigidly suppressing isolated neurons or features. However, harmful semantics manifest as distributed, cross-layer circuits, rendering localized ablations both brittle against complex jailbreaks and detrimental to general utility. To bridge this gap, we propose TraceRouter++, a routing-level safety intervention framework that explicitly traces safety-relevant causal routing pathways activated under harmful inputs and realigns their unsafe activation states. Our framework operates in a Discover-Trace-Realign paradigm: it first pinpoints a sensitive onset layer via attention divergence and disentangles dense activations into interpretable routing features using sparse autoencoders (SAEs). Subsequently, it maps these features to downstream causal circuits via feature influence scores (FIS). Crucially, departing from rigid suppression paradigms, TraceRouter++ introduces a constrained optimal transport (OT)-based soft routing realignment. By formulating safety intervention as a tractable coordinate-wise marginal optimal transport approximation, our method redirects unsafe activation marginals toward safe-reference marginals within causally identified routing subspaces while preserving non-selected coordinates at the intervention point. This mechanism safely redirects malicious semantic flows while leaving orthogonal computational routes intact. Extensive experiments across representative large language models (LLMs), multimodal large language models (MLLMs), and diffusion models (DMs) show that TraceRouter++ outperforms evaluated baselines, improving adversarial robustness while maintaining a favorable safety-utility trade-off. WARNING: This paper contains unsafe model responses.