LLM Safety

LLM: Large Language Model

LLM safety studies how models can avoid harmful assistance, manipulation, privacy violations, and unreliable advice while still helping with legitimate requests. Approaches include safety training and data filtering, inference-time guardrails and steering, output monitoring, and mechanistic methods that probe or edit internal representations. Benchmarks increasingly test jailbreaks across languages and modalities, long conversations, tool use, and high-stakes settings such as health and cybersecurity. A central challenge is maintaining robustness against adaptive attacks and changing contexts without causing over-refusal or sacrificing utility.

Latest papers

442 papers68 papers in the last four weeks, up 70% on the four weeks before. 0.4% of all new papers.

Chain-of-Authorization: Embedding authorization into large language models
Mar 24, 2026Yang Li, Yule Liu, Xinlei He +3LLM Security LLM Safety
Department of Computer Science and Technology, Tsinghua University . · Data Science and Analytic Thrust, Information Hub, The Hong Kong University of Science and Technology (Guangzhou) . · Institude for Math and AI, Wuhan University .
LLMON: An LLM-native Markup Language to Leverage Structure and Semantics at the LLM Interface
Mar 23, 2026Michael Hind, Basel Shbita, Bo Wu +5Structured Prompting LLM Prompting
IBM Research Yorktown Heights, New York · IBM Research San Jose, California · IBM Research Cambridge, Massachusetts
SecureBreak -- A dataset towards safe and secure models
Mar 23, 2026Marco Arazzi, Vignesh Kumar Kembu, Antonino NoceraLLM Safety Language Model Safety Evaluation
Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Italy
SafePilot: A Framework for Assuring LLM-enabled Cyber-Physical Systems
Mar 23, 2026Weizhe Xu, Mengyu Liu, Fanxin KongLLM Safety Cyber-Physical Systems
University of Notre Dame, Notre Dame, IN, USA · Washington State University, Richland, WA, USA
Evolving Jailbreaks: Automated Multi-Objective Long-Tail Attacks on Large Language Models
Mar 20, 2026Wenjing Hong, Zhonghua Rong, Li Wang +5Jailbreak Attacks LLM Jailbreak Attacks
School of Artificial Intelligence Shenzhen Univeristy, China · Brain-Inspired Technology Co.,Ltd, China · Department of Computer Science and Engineering Southern University of Science and Technology, China +1
Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis
Mar 20, 2026May Lynn Reese, Markela Zeneli, Mindy Ng +3LLM Safety LLM Safety Evaluation
Apart Research · Odyssean Institute · London School of Economics and Political Science +1
Box Maze: A Process-Control Architecture for Reliable LLM Reasoning
Mar 19, 2026Zou QiangLLM Safety Reasoning Consistency in Language Models
1Independent Researcher
Toward Reliable, Safe, and Secure LLMs for Scientific Applications
Mar 18, 2026Saket Sanjeev Chaturvedi, Joshua Bergerson, Tanwi MallickLLM Safety AI Agent Safety
Argonne National Laboratory, Lemont, 60439, USA
Multi-Trait Subspace Steering to Reveal the Dark Side of Human-AI Interaction
Mar 18, 2026Xin Wei Chia, Swee Liang Wong, Jonathan PanHuman-AI Interaction LLM Safety
Home Team Science & Technology Agency (HTX) Singapore
Large Language Models as a Semantic Interface and Ethical Mediator in Neuro-Digital Ecosystems: Conceptual Foundations and a Regulatory Imperative
Mar 18, 2026Alexander V. Shenderuk-Zhidkov, Alexander E. HramovLLM Safety
Immanuel Kant Baltic Federal University, 14 A. Nevskogo street, Kaliningrad, 236041, Russia. · Plekhanov Russian University of Economics, 36 Stremyanny Lane, Moscow, 115054, Russia. · Pirogov National Medical and Surgical Center, 70 Nizhnyaya Pervomayskaya street, Moscow, 105203, Russia.
Characterizing Delusional Spirals through Human-LLM Chat Logs
Mar 17, 2026Jared Moore, Ashish Mehta, William Agnew +11LLM Safety
Stanford University Stanford, California, USA · Carnegie Mellon University Pittsburgh, Pennsylvania, USA · University of Chicago Chicago, Illinois, USA +5
Structured Semantic Cloaking for Jailbreak Attacks on Large Language Models
Mar 17, 2026Xiaobing Sun, Perry Lam, Shaohua Li +4Adversarial Attacks on LLMs LLM Jailbreak Attacks
Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore. · Information Systems Technology and Design Pillar, Singapore University of Technology and Design.
Re-Mask and Redirect: Exploiting Denoising Irreversibility in Diffusion Language Models
Mar 17, 2026Arth SinghAdversarial Attacks on LLMs Adversarial Attacks on Diffusion Models
AIM Intelligence · National Institute of Technology Agartala
Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph
Mar 16, 2026Zhenheng Tang, Xiang Liu, Qian Wang +3LLM Alignment LLM Safety
The Hong Kong University of Science and Technology · The Hong Kong University of Science and Technology (Guangzhou) · New York University +1
Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities
Mar 16, 2026Vanshaj Khattar, Md Rafi ur Rashid, Moumita Choudhury +4Test-Time RL LLM Safety
Virginia Tech · Penn State University · University of Massachusetts Amherst +1
Beyond Creed: A Non-Identity Safety Condition A Strong Empirical Alternative to Identity Framing in Low-Data LoRA Fine-Tuning
Mar 16, 2026Xinran ZhangSafety-Preserving Fine-Tuning of Language Models LLM Safety
University of California, Berkeley
Exposing Long-Tail Safety Failures in Large Language Models through Efficient Diverse Response Sampling
Mar 15, 2026Suvadeep Hajra, Palash Nandi, Tanmoy ChakrabortyLLM Safety LLM Red Teaming
Department of Electrical Engineering, Indian Institute of Technology Delhi · Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi
State-Dependent Safety Failures in Multi-Turn Language Model Interaction
Mar 15, 2026Pengcheng Li, Jie Zhang, Tianwei Zhang +5LLM Safety Language Model Safety Evaluation
School of Cyber Science and Technology, University of Science and Technology of China, China · Agency for Science, Technology and Research (A*STAR), Singapore · Nanyang Technological University, Singapore +3
Relationship-Aware Safety Unlearning for Multimodal LLMs
Mar 15, 2026Vishnu Narayanan Anilkumar, Abhijith Sreesylesh Babu, Trieu Hai Vo +2MLLM Unlearning LLM Safety
Florida International University
Front-End Ethics for Sensor-Fused Health Conversational Agents: An Ethical Design Space for Biometrics
Mar 14, 2026Hansoo Lee, Rafael A. CalvoConversational Agents Human-Centered AI
Imperial College London London, UK · Korea Institute of Science and Technology Republic of Korea
Understanding LLM Behavior When Encountering User-Supplied Harmful Content in Harmless Tasks
Mar 12, 2026Junjie Chu, Yiting Qu, Ye Leng +4LLM Safety Language Model Safety Evaluation
CISPA Helmholtz Center for Information Security · Flexera · Delft University of Technology
Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Services
Mar 11, 2026Fabrizio Dimino, Bhaskarjit Sarmah, Stefano PasqualiLanguage Model Safety Evaluation LLM Safety
1Domyn, New York, US · 2Domyn, New York, US · 3Domyn, New York, US
GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning
Mar 10, 2026Zhouxiang Fang, Jiawei Zhou, Hanjie ChenSafety-Preserving Fine-Tuning of Language Models LLM Safety Alignment
Rice University · Stony Brook University
Do Large Language Models Get Caught in Hofstadter-Mobius Loops?
Mar 10, 2026Jaroslaw HryszkoLLM Safety Framing Effects in Language Models
Faculty of Mathematics and Computer Science, Jagiellonian University, Krak´ow, Poland
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
Amnesia: Adversarial Semantic Layer Specific Activation Steering in Large Language Models
Mar 10, 2026Ali Raza, Gurang Gupta, Nikolay Matyunin +1Adversarial Attacks on LLMs LLM Jailbreak Attacks
Honda Research Institute Europe Offenbach, Hesse, Germany · IIT KharagPur Kharagpur, India
Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms
Mar 10, 2026Mingjie Li, Wai Man Si, Michael Backes +2LLM Safety LLM Safety Alignment
CISPA Helmholtz Center for Information Security · State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · Institute for Artificial Intelligence, Peking University
Bioalignment: Measuring and Improving LLM Disposition Toward Biological Systems for AI Safety
Mar 10, 2026Trent R Northen, Mingxun WangLLM Alignment LLM Safety
Bioaligned Labs · Lawrence Berkeley National Lab · Computer Science & Engineering Dept, UC Riverside
CORE-Acu: Structured Reasoning Traces and Knowledge Graph Safety Verification for Acupuncture Clinical Decision Support
Mar 9, 2026Liuyi Xu, Yun Guo, Ming Chen +5Structured CoT Reasoning Clinical Decision Support
College of Information Science and Engineering, Northeastern University, Shenyang 110819, China · School of Information Science and Engineering, Yanshan University, Qinhuangdao, Hebei 066000, China · School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China +3
Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs
Mar 8, 2026Yige Li, Wei Zhao, Zhe Li +6LLM Safety LLM Safety Benchmarks
Singapore Management University · The University of Melbourne · Fudan University

Mar 24, 2026J/K move · Enter open · S save

Chain-of-Authorization: Embedding authorization into large language models

Yang Li, Yule Liu, Xinlei He, Youjian Zhao+2

Department of Computer Science and Technology, Tsinghua University . · Data Science and Analytic Thrust, Information Hub, The Hong Kong University of Science and Technology (Guangzhou) . · Institude for Math and AI, Wuhan University .

LLM Security LLM Safety Adversarial Robustness of Language Models

Open paper AskPDF arXiv

Although Large Language Models (LLMs) have evolved from text generators into the cognitive core of modern AI systems, their inherent lack of authorization awareness exposes these systems to catastrophic risks, ranging from unintentional data leakage to unauthorized command execution. Existing defense mechanisms are fundamentally decoupled from internal reasoning, rendering them insufficient for the complex security demands of dynamic AI systems. Here, we propose the Chain-of-Authorization (CoA) framework, a paradigm that internalizes access control as a foundational cognitive capability. By systematically redesigning the input-output format and fine-tuning the model on synthesized data with complex permission topologies, CoA forces the model to generate a structured authorization trajectory as a causal prerequisite for any substantive response or action, thereby enabling LLMs to internalize access boundaries within dynamic reasoning environments. CoA maintains high utility in authorized scenarios while achieving high rejection rates of unauthorized prompts and robust defense against diverse adversarial attacks. By embedding authorization directly into the reasoning process, CoA provides a principled architectural blueprint for deploying secure LLMs as the cognitive cores of modern AI systems.