Guardrail

Ask about this topic

Momentum

7 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 50

All topics
CardsList

  1. ReF-HIL: Shaping the Critic around Human Action Neighborhoods for Efficient Human-in-the-Loop Reinforcement Learning

    Sep 29, 2026Shaoyin Luo, Song Wang, Shibo Xia +5Reinforcement Learning From Human FeedbackHuman-In-The-Loop

    Department of Mechanical Engineering, Tsinghua University, Beijing 100084, China

  2. InGuard: Towards Generalized Inner Guardrail for Safe Text-to-Image Generation

    Sep 23, 2026Zeyu Wang, Xiaodan Li, Zhiwen Li +2Text-To-ImageGuardrail

    Alibaba AAIG

  3. Learning Beyond What Humans Can Demonstrate

    Sep 21, 2026Yuchen Song, Aditya Mittal, Unnat JainTeleoperationBehavior Cloning

    University of California, Irvine

  4. Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models

    Sep 16, 2026Alizishaan Khatri, Chiquita Prabhu, Omkar NeogiLarge Language Model SafetyGuardrail

    Wrynx Inc. · Independent Researcher

  5. Overflip: Repetition-Induced Label Flips in Guardrail Models

    Sep 14, 2026Xu He, Chih-Hsuan Lin, Hung-Mao Chen +3FlipsGuardrail

    1George Mason University · 2Virginia Tech · 3Missouri University of Science and Technology +1

  6. Guardrailed Meta-Agent Loops: Stress-Testing Policy Pinning, Budget Bounds, and Crash Recovery

    Sep 14, 2026Qinzhen Ma, Jialin WuAgent LoopGuardrail

    Rice University · University of California, San Diego

  7. Suan: Rectifying Direct Preference Safety Alignment in Large Language Models

    Sep 8, 2026Oleksandr Cherednichenko, Roman KlypaSafety AlignmentLarge Language Model Alignment

    Department of Mathematics and Mathematical Statistics Integrated Science Lab, Umeå University Umeå, Sweden · Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK 38000 Grenoble, France

  8. When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluation

    Sep 1, 2026Peiying Zhu, Sidi ChangAgentic EvaluationsFrontier Large Language Model Agents

    Blossom AI · San Francisco, CA, USA · Blossom AI Labs +1

  9. HiveTraceGuard-Pro: A Compact Generative Guardrail for Prompt Injection, Jailbreaks, and Adversarial Obfuscation

    Sep 1, 2026Nikita Oblakov, Sabrina Sadiekh, Evgeniy KokuykinPrompt-Injection DetectorsGuardrail

    HiveTraceLab

  10. SingProbe Technical Report

    Aug 31, 2026Sing TeamLarge Language Model SafetyRuntime Safety Filtering

    AI Security Lab, Ant Group

  11. Influence Is Not Authority: When Causal Guardrail Signals Make Legitimate Tool Use Look Like an Attack in Tool-Using LLM Agents

    Aug 30, 2026Tanzim Ahad, Ismail Hossain, Md Jahangir Alam +3Controlling Tool UseGuardrail

    Department of Computer Science, University of Texas at El Paso, TX, USA 79902 · Department of Computer Science and Engineering, New Mexico Tech, Socorro, NM, USA 87801 · University of Illinois Urbana-Champaign, IL, USA

  12. LongGuard: Mechanistic Analysis and Training-Free Mitigation of Long-Context Failure in Safety Guardrails

    Aug 27, 2026Ziyang Chen, Xing Wu, Songlin HuGuardrailLarge Language Model Safety

    Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China

  13. Reflex-Guard: A Low-Latency Guardrail for LLM Prompt Safety Using Dense Semantic Embeddings

    Aug 18, 2026Istiaque Ahmed, Afia Anjum Borsha, Ranat Das Prangon +2Large Language Model SafetyGuardrail

    Graduate School of Informatics, Osaka Metropolitan University, Osaka 558-8585, Japan · Dept. of Computer Science and Engineering, BRAC University, Dhaka 1212, Bangladesh · Dept. of Chemical Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka 1000, Bangladesh +1

  14. ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions

    Aug 11, 2026Xinzhe Huang, Biwu Yao, Kedong Xiu +4Large Language Model SafetyGuardrail

    State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China · Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Hangzhou, China · University of Electronic Science and Technology of China, Chengdu, China +3

  15. Yesterday's Shield, Today's Spear: A Self-Evolving Safety Guardrail in Production

    Aug 9, 2026Cong Ming, Jingyi Chen, Bin Liu +4GuardrailLarge Language Model Safety

    University of Science and Technology of China · Shenzhen University · Sangfor Technologies

  16. ECHO: A Locally-Deployable Agentic Health Assistant with Temporal Memory, Safety Guardrails, and Speech Assessment

    Aug 6, 2026Abdulkadir Külçe, Alihan Esen, Çağla Fikir +4HealthcareGuardrail

    Dept. of Artificial Intelligence and Data Engineering, Istanbul Technical University, Istanbul, Turkey · Dept. of Computer Engineering, Istanbul Technical University, Istanbul, Turkey

  17. When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation

    Jul 23, 2026Dongbin NaStreaming GuardrailsGuardrail

    POSTECH

  18. GuardianAgentBench: Where Agents Fail and How to Guard Them

    Jul 23, 2026Vishal Ishwar Naik, Chenyu Xu, Donna Dong +5Agentic BenchmarksLarge Language Model Safety

    Vectara, Inc., Palo Alto, CA, USA · Iowa State University, Ames, IA, USA

  19. Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents

    Jul 21, 2026Aarushi SinghLarge Language Model SafetyUntrusted Content

    Independent Researcher India

  20. A Dual-Hypothesis Reasoning Framework for LLM Guardrails

    Jul 20, 2026Md Asiful Islam, Mihai SurdeanuLarge Language Model SafetyGuardrail

    Department of Computer Science University of Arizona, USA

  21. SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification

    Jul 13, 2026SingGuard TeamStreaming GuardrailsGuardrail

    AI Security Lab, Ant Group

  22. PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails

    Jul 7, 2026Mingyang Song, Luxin Xu, Haoyu Sun +3Streaming GuardrailsGuardrail

    1Fudan University · 2Tongji University · 3Virtue AI +3

  23. Integrated Graph Search and Model Predictive Control for Smooth and Efficient Path Planning in Autonomous Vehicles

    Jul 5, 2026Duc-Tien Bui, Ngoc Thinh Nguyen, Hung Duy Nguyen +3Path PlanningVehicle Dynamics

    Institute of Automotive Engineering, Graz University of Technology, 8010 Graz, Austria · Drone Engineering, University of Applied Science Kufstein Tirol, Austria · Automation and Control Institute (ACIN), Vienna University of Technology, Austria

  24. Criticality-Based Guard Rail Validation for AI Agent Decisions in Autonomous Telecom Networks

    Jul 2, 2026Ravi Kant SharmaGuardrailMobile Networks

    Ericsson

  25. Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring

    Jul 2, 2026William Hackett, Peter GarraghanGuardrailLarge Language Model Safety

    Mindgard · Lancaster University

  26. Do Safety Guardrails Need to Reason? LeanGuard: A Fast and Light Approach for Robust Moderation

    Jun 25, 2026Dongbin NaGuardrailLarge Language Model Safety

    POSTECH

  27. Neuro-Symbolic Agents for Regulated Process Automation: Challenges and Research Agenda

    Jun 11, 2026Alexander Rombach, Chantale Lauer, Nijat MehdiyevNeuro-Symbolic FrameworkAutomated

    German Research Center for Artificial Intelligence (DFKI), Campus D3 2, 66123 Saarbrücken, Germany · Saarland University, Campus D3 2, 66123 Saarbrücken, Germany

  28. Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails

    Jun 4, 2026Marco Antonio Stranisci, A Pranav, Rossana Damiano +2Large Language Model BiasGuardrail

    University of Turin, Italy · Trustworthy AI Lab, University of Hamburg, Germany · IT University of Copenhagen, Denmark

  29. From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents

    Jun 4, 2026Yuhao Sun, Jiacheng Zhang, Shaanan Cohney +3GuardrailLarge Language Model Safety

    1The University of Melbourne · 2Tsinghua University · †Corresponding author.

  30. Long-Term and Short-Term Transistor Aging in Deep Neural Networks: Impact and Mitigation

    Jun 2, 2026Alireza Sarmadi, Virinchi Roy Surabhi, Prashanth Krishnamurthy +3Neural Network InferencePrinted Circuit Board

    Dept. of Electrical and Computer Engineering, New York University (NYU) Tandon School of Engineering, New York, USA · School of Computation, Information and Technology, Technical University of Munich (TUM), Munich, Germany

  31. Compliance-Scored Best-of-N Guardrail Orchestration for Multimodal Document Generation in Payments Dispute Defense

    Jun 1, 2026Nataraj Agaram Sundar, Tejas MorabiaStreaming GuardrailsGuardrail

    eBay Inc. San Jose, CA, USA

  32. EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents

    May 29, 2026Dongwook Choi, Taeyoon Kwon, Bogyung Jeong +6Embodied AgentsHazard

    Department of Artificial Intelligence, Yonsei University · Department of Biomedical Engineering and the Department of Intelligent Precision Healthcare Convergence, Sungkyunkwan University · Independent Researcher

  33. Triaging Threats to Specialized Guardrails

    May 29, 2026Wenjie Jacky Mo, Xiaofei Wen, Rui Cai +6GuardrailLarge Language Model Safety

    University of California, Davis

  34. Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content

    May 28, 2026Ihor Stepanov, Aleksandr SmechovLarge Language Model SafetyGuardrail

    1Knowledgator, Kyiv, Ukraine · 2Wordcab, New York, USA

  35. Robust and Efficient Guardrails with Latent Reasoning

    May 27, 2026Siddharth Sai, Xiaofei Wen, Muhao ChenLarge Language Model SafetyGuardrail

    University of California, Davis

  36. Test-Time Training Undermines Safety Guardrails

    May 21, 2026Simone Antonelli, Sadegh Akhondzadeh, Aleksandar BojchevskiInference-Time DefenseTest-Time Training

    CISPA Helmholtz Center for Information Security · University of Cologne

  37. CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety

    May 20, 2026Heajun An, Qi Zhang, Vedanth Achanta +1Large Language Model SafetyGuardrail

    Virginia Tech

  38. Robotics-Inspired Guardrails for Foundation Models in Socially Sensitive Domains

    May 19, 2026Rebecca Ramnauth, Drazen Brscic, Brian ScassellatiGuardrailComplex Societies

    Yale University, USA · Kyoto University, Japan

  39. Why Do Safety Guardrails Degrade Across Languages?

    May 16, 2026Max Zhang, Ameen Patel, Sang T. Truong +1Multilingual SafetyLarge Language Model Safety

    Stanford University

  40. LiSA: Lifelong Safety Adaptation via Conservative Policy Induction

    May 14, 2026Minbeom Kim, Lesly Miculicich, Bhavana Dalvi Mishra +6Artificial Intelligence SafetyGuardrail

    Google Cloud AI Research · Google · Seoul National University

  41. LLM-Based Persuasion Enables Guardrail Override in Frontier LLMs

    May 13, 2026Rodrigo Nogueira, Thales Sales Almeida, Giovana Kerche Bonás +7Argumentation FrameworksElicitation

    Maritaca AI · JusBrasil

  42. Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs

    May 11, 2026Krishak Aneja, Manas Mittal, Anmol Goel +2Emergent MisalignmentLarge Language Model Alignment

    International Institute of Information Technology, Hyderabad · TU Darmstadt · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi

  43. Behavioral Determinants of Deployed AI Agents in Social Networks: A Multi-Factor Study of Personality, Model, and Guardrail Specification

    May 8, 2026Sarah Wilson, Diem Linh Dang, Usman Ali Moazzam +2Artificial Intelligence AgentsSocial Media

    Columbia University

  44. GLiGuard: Schema-Conditioned Classification for LLM Safeguard

    May 8, 2026Urchade Zaratiana, Mary Newhauser, George Hurn-Maloney +1Large Language Model SafetyStreaming Guardrails

    Fastino Labs

  45. BabelSafe: A Policy-Grounded Multilingual Safety Benchmark for LLMs

    May 1, 2026Yunhan Zhao, Zhaorun Chen, Xingjun Ma +1Multilingual SafetyLarge Language Model Safety

    University of Illinois Urbana-Champaign · Fudan University · University of Chicago

  46. BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate

    Apr 28, 2026Arnon Mazza, Elad LeviStreaming GuardrailsSynthetic Training Data

    Plurai Inc.

  47. Guardrails in Logit Space: Safety Token Regularization for LLM Alignment

    Apr 19, 2026Thong Bach, Truyen TranSafety AlignmentLarge Language Model Alignment

    Applied Artificial Intelligence Initiative (A2I2), Deakin University

  48. Proof-of-Guardrail in AI Agents and What (Not) to Trust from It

    Mar 6, 2026Xisen Jin, Michael Duan, Qin Lin +4On-Chain AttestationsGuardrail

    Sahara AI · University of Southern California

  49. 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

    Alibaba-AAIG

  50. NeuroFilter: Activation-Based Guardrails for Privacy-Conscious LLM Agents

    Jan 21, 2026Saswat Das, Ferdinando FiorettoPrivacyGuardrail

    University of Virginia