Large Language Model Safety

Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

27 new papers

A weekly snapshot of new work published in Large Language Model Safety.

Period ending 2026-09-14

12 new papers

A weekly snapshot of new work published in Large Language Model Safety.

Inside this field

Focused directions

855 papers

Latest in Large Language Model Safety

Browse all topics →
CardsList

  1. Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization

    Apr 16, 2026Haochun Tang, Yuliang Yan, Jiahua Lu +2Large Language Model RoutingLanguage Model Evasion Attacks

  2. Benchmarks for Trajectory Safety Evaluation and Diagnosis in OpenClaw and Codex: ATBench-Claw and ATBench-Codex

    Apr 16, 2026Zhonghao Yang, Yu Li, Yanxu Zhu +6Safety EvaluationAgentic Benchmarks

  3. Bounded Autonomy for Enterprise AI: Typed Action Contracts and Consumer-Side Execution

    Apr 16, 2026Sarmad Sohail, Ghufran HaiderEnterprise SystemsLarge Language Model Safety

  4. CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification

    Apr 16, 2026Yian Wang, Yuen Chen, Agam Goyal +1DetoxificationToxicity

  5. VoxSafeBench: Not Just What Is Said, but Who, How, and Where

    Apr 16, 2026Yuxiang Wang, Hongyu Liu, Yijiang Xu +9Large Language Model Safety

  6. HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models

    Apr 14, 2026Zixing Chen, Yifeng Gao, Li Wang +8Large Language Model Safety

  7. ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems

    Apr 13, 2026Daeyeon SonLarge Language Model SafetyLLM Inference Efficiency

  8. Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types

    Apr 10, 2026Hadas Orgad, Boyi Wei, Kaden Zheng +4Large Language Model SafetyLarge Language Model Alignment

  9. How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models

    Apr 6, 2026Gregory N. FrankLarge Language Model SafetyLarge Language Model Alignment

  10. TSHA: A Benchmark for Visual Language Models in Trustworthy Safety Hazard Assessment Scenarios

    Mar 31, 2026Qiucheng Yu, Ruijie Xu, Mingang Chen +2HazardLarge Language Model Safety

  11. Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models

    Mar 28, 2026Kaishen Wang, Heng HuangUnified Multimodal ModelsLarge Language Model Safety

  12. SafeMath: Safe Solutions for Unsafe Math Word Problems

    Mar 26, 2026Sagnik Basu, Subhrajit Mitra, Aman Juneja +3Large Language Model SafetyMath Problems

  13. T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search

    Mar 21, 2026Hyomin Lee, Sangwoo Park, Yumin Choi +3Language Model Evasion AttacksRed-Teaming

  14. SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems

    Mar 18, 2026Rima Hazra, Bikram Ghuku, Ilona Marchenko +5Large Language Model Safety

  15. Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating

    Mar 13, 2026Xiangkui Cao, Jie Zhang, Meina Kan +2Large Language Model SafetyLarge Vision Language Models

  16. Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Services

    Mar 11, 2026Fabrizio Dimino, Bhaskarjit Sarmah, Stefano PasqualiLarge Language Model SafetyRed-Teaming

  17. AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models

    Mar 9, 2026Hankun Kang, Di Lin, Zhirong Liao +6Large Language Model SafetyCultural Knowledge

  18. Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization

    Mar 9, 2026Hongli Zhou, Hui Huang, Rui Zhang +5JudgesImplicit Bias

  19. From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions

    Mar 9, 2026Rishab Alagharu, Ishneet Sukhvinder Singh, Shaibi Shamsudeen +2RefusalsLarge Language Model Safety

  20. MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models

    Mar 3, 2026Zhongxi Wang, Yueqian Lin, Jingyang Zhang +3Large Language Model SafetyLarge Language Model Evaluation

  21. Prompt Injection as Role Confusion

    Feb 22, 2026Charles Ye, Jasmine Cui, Dylan Hadfield-MenellIndirect Prompt InjectionLanguage Model Evasion Attacks

  22. Sparse Autoencoders are Capable LLM Jailbreak Mitigators

    Feb 12, 2026Yannick Assogba, Jacopo Cortellazzi, Javier Abad +3Novel Jailbreak MethodLarge Language Model Safety

  23. Robustness of Vision Language Models Against Split-Image Harmful Input Attacks

    Feb 8, 2026Md Rafi Ur Rashid, MD Sadik Hossain Shanto, Vishnu Asutosh Dasu +1Large Vision Language ModelsAdversarial Jailbreaks

  24. Endogenous Resistance to Activation Steering in Language Models

    Feb 6, 2026Alex McKenzie, Keenan Pepper, Stijn Servaes +6Activation SteeringLarge Language Model Safety

  25. CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation

    Feb 4, 2026Zhao Tong, Chunlin Gong, Yiping Zhang +5Large Language Model SafetyLarge Language Model Reasoning

  26. CC-ΔΘΔΘ: Circuit-Restricted Weight Arithmetic for Selective Refusal

    Feb 4, 2026Aditya Kasliwal, Pratinav Seth, Vinay Kumar SankarapuRefusalsStreaming Guardrails

  27. HALT: Hallucination Assessment via Log-probs as Time series

    Feb 2, 2026Ahmad Shapiro, Karan Taneja, Ashok GoelHallucination DetectionHallucination Rate

  28. Verifiable Manifest Signing and Transparency Enforcement for Secure MCP-Based LLM Pipelines

    Jan 30, 2026Saeid Jamshidi, Kawser Wazed Nafi, Arghavan Moradi Dakhel +2Large Language Model SafetyModel Context Protocol

  29. From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching

    Jan 30, 2026Zhixiang Zhang, Zesen Liu, Yuchong Xie +2Language Model Evasion AttacksCache

  30. AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs

    Jan 30, 2026Jaehee Kim, Pilsung KangLanguage Model Evasion AttacksAI Privacy Risks and Protection

  31. Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs

    Jan 29, 2026Xiang Zheng, Yutao Wu, Hanxun Huang +5Language Model Evasion AttacksCoding Agents

  32. Health-ORSC-Bench: A Benchmark for Measuring Over-Refusal and Safety Completion in Health Context

    Jan 25, 2026Zhihao Zhang, Liting Huang, Guanghao Wu +3Large Language Model SafetyRefusals

  33. YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models

    Jan 22, 2026Junyu Lin, Meizhen Liu, Xiufeng Huang +12Large Language Model SafetyGuardrail

  34. HardSecBench: Benchmarking the Security Awareness of LLMs for Hardware Code Generation

    Jan 20, 2026Qirui Chen, Jingxian Shuai, Shuangwu Chen +8Hardware Description LanguagesSecurity Analysis

  35. OI-Bench: An Option Injection Benchmark for Evaluating LLM Susceptibility to Directive Interference

    Jan 19, 2026Yow-Fu Liou, Yu-Chien Tang, Yu-Hsiang Liu +1Large Language Model SafetyInterference

  36. Preserving Fairness and Safety in Quantized LLMs Through Critical Weight Protection

    Jan 17, 2026Muhammad Alif Al Hakim, Alfan Farizki Wicaksono, Fajri KotoLarge Language Model QuantizationLarge Language Model Safety

  37. Test-Time Detoxification without Training or Learning Anything

    Jan 14, 2026Baturay Saglam, Dionysis KalogeriasToxicityDetoxification

  38. Safe Language Generation in the Limit

    Jan 13, 2026Antonios Anastasopoulos, Giuseppe Ateniese, Evgenios M. KornaropoulosLarge Language Model Safety

  39. Safety Is Not Universal: The Selective Safety Trap in LLM Alignment

    Jan 7, 2026Iago Alves Brito, Walcy Santos Rezende Rios, Julia Soares Dollis +2Large Language Model SafetyLarge Language Model Alignment

  40. Hidden State Poisoning Attacks against Mamba-based Language Models

    Jan 5, 2026Alexandre Le Mercier, Chris Develder, Thomas DemeesterLanguage Model Evasion AttacksBidirectional Mamba

  41. The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety

    Jan 3, 2026Ian Rios-SialerDiversityLarge Language Model Safety

  42. SecureCode: A Production-Grade Multi-Turn Dataset for Training Security-Aware Code Generation Models

    Dec 20, 2025Scott ThorntonVulnerable CodeCode Generation

  43. SGM: Safety Glasses for Multimodal Large Language Models via Neuron-Level Detoxification

    Dec 17, 2025Hongbo Wang, AprilPyone MaungMaung, Isao EchizenToxicityLarge Language Model Safety

  44. Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs

    Dec 3, 2025Oren Rachmil, Avishag Shapira, Roy Betser +5Large Language Model SafetyViolation

  45. Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks

    Dec 2, 2025Songwen Zhao, Danqing Wang, Kexun Zhang +3Vibe CodingVulnerable Code

  46. Epistemic Bias Injection: Manipulating LLM Opinion via Selective Context Retrieval

    Nov 30, 2025Hao Wu, Prateek SaxenaLarge Language Model BiasLanguage Model Evasion Attacks

  47. Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety

    Oct 18, 2025Vamshi Krishna Bonagiri, Ponnurangam Kumaragurum, Khanh Nguyen +1Large Language Model AgentsLarge Language Model Safety

  48. SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses

    Oct 17, 2025Hanbin Hong, Shuang Wu, Shuya Feng +6Large Language Model SafetyLarge Language Model Evaluation

  49. Echoes of Human Malice in Agents: Benchmarking LLMs for Multi-Turn Online Harassment Attacks

    Oct 16, 2025Trilok Padhi, Pinxian Lu, Abdulkadir Erol +5Language Model Evasion AttacksMulti-Turn Interactions

  50. Toward Cybersecurity-Expert Small Language Models

    Oct 15, 2025Matan Levi, Daniel Ohayon, Ariel Blobstein +3CybersecurityLarge Language Model Safety

  51. CogniDir: Combating Cognitive Malicious Comments via Adaptive Distributional Learning for Robust Fake News Detection

    Oct 10, 2025Zhao Tong, Chunlin Gong, Yimeng Gu +5Fake News DetectionLanguage Model Evasion Attacks

  52. SafetyFlow: An Agent-Flow System for Automated LLM Safety Benchmarking

    Aug 21, 2025Xiangyang Zhu, Yuan Tian, Chunyi Li +3Large Language Model Safety

  53. Let's Measure Information Step-by-Step: AI-Based Evaluation Beyond Vibes

    Aug 7, 2025Zachary Robertson, Sanmi KoyejoAdversarial EvaluationVibe Coding

  54. Data Security in Large Language Models: Risks, Defense, and Directions

    Aug 4, 2025Kang Chen, Xiuze Zhou, Yuanhui Yu +4Large Language Model SafetyAdversarial Training

  55. Measuring Harmfulness of Computer-Using Agents

    Jul 31, 2025Aaron Xuxiang Tian, Ruofan Zhang, Janet Tang +3Large Language Model Safety

  56. Addressing Benchmarking Gaps in Large Language Models for Health and Medicine with Dynamic Red-Teaming

    Jul 30, 2025Jiazhen Pan, Bailiang Jian, Paul Hager +20Large Language Model SafetyRed-Teaming

  57. LLMs Encode Harmfulness and Refusal Separately

    Jul 16, 2025Jiachen Zhao, Jing Huang, Zhengxuan Wu +2Large Language Model SafetyRefusals

  58. LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing

    Jul 5, 2025Jiahao Chen, Junhao Li, Yiming Wang +6Adversarial PromptingText-To-Image Diffusion Models

  59. Less Data, More Security: Advancing Cybersecurity LLMs Specialization via Resource-Efficient Domain-Adaptive Continuous Pre-training with Minimal Tokens

    Jun 30, 2025Salahuddin Salahuddin, Ahmed Hussain, Jussi Löppönen +1CybersecurityLarge Language Model Safety

  60. RedCoder: Automated Multi-Turn Red Teaming for Code LLMs

    Jun 25, 2025Wenjie Jacky Mo, Qin Liu, Xiaofei Wen +5Red-TeamingCode Generation