Safety Filtering

Ask about this topic

Momentum

24 papers in the last four weeks, up 118% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 111

All topics
CardsList

  1. Context-Conditioned Hamilton-Jacobi Reachability for Adaptive Safety Filtering

    Oct 6, 2026Ali Fuat Sahin, Yunus Yazoglu, John Talbot +3Reachability AnalysisAutonomous Driving Safety Evaluation

    Ecole Polytechnique Fédérale de Lausanne · Stanford University · Toyota Research Institute

  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 ModelsSafety Filtering

    University of Washington · New York University

  3. A Safe Prototype Is Not a Safety Direction: Reference Dependence and Prompt Confounds in Response-Safety Embeddings

    Oct 1, 2026Sahil KadadekarPrototype-Based ClassificationLLM Evaluation

    New York University

  4. Multi-Link Safety Filtering for VLA Policies Around Moving Hazards

    Sep 30, 2026Yatharth Agarwal, Vijay RaghunathanRobot SafetySafety Filtering

    School of Electrical and Computer Engineering Purdue University, West Lafayette, IN, USA

  5. Guard Models Are Overconfident Where Base Models Are Uncertain

    Sep 29, 2026Jonghyun Hong, MinJae Jung, Minwoo KimLanguage Model Safety EvaluationAdversarial Attacks on LLMs

    DATUMO INC.

  6. Adaptive Safety Filtering for Frozen ACC Policies via Conformal Residual Calibration

    Sep 28, 2026Zhiruo Zhou, Rigaudiere Z. Li, Chen Xiwen +3Safety-Critical ControlAutonomous Driving Safety Evaluation

    Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Wuhan University of Technology, Wuhan, China · Shanghai Jiao Tong University, Shanghai, China

  7. Predictive Semantic Safety: From Visual Physical Reasoning to Safety-Critical Control

    Sep 28, 2026Taekyung Kim, Salem Fradi, Yanning Dai +2Robotic ControlSafety-Critical Control

    Department of Robotics, University of Michigan, Ann Arbor, MI 48109, USA · Center of Excellence in Generative AI, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia. · Dalle Molle Institute for Artificial Intelligence Research (IDSIA), Switzerland. +2

  8. When World Models Lie: Adaptive Safety Analysis Under Wrong Imaginations

    Sep 28, 2026John Cao, Somil BansalReachability AnalysisWorld Models for Robotics

    Department of Aeronautics and Astronautics, Stanford University

  9. AdaGuard: An Adaptive Guard Model with User-defined Policies

    Sep 28, 2026Yunhao Feng, Yifan Ding, Yuxiang Xie +4LLM GuardrailsAI Agent Safety

    National University of Defense Technology · Fudan University

  10. COGNIT-Guard: Calibrated Standalone Direct-Decision Guardrails with Heterogeneous CPU-NPU Confidence Cascading under Explicit Latency and False-Positive Constraints

    Sep 27, 2026Hao ChenLLM GuardrailsLanguage Model Calibration

    School of Cyber Security, Guangdong Polytechnic Normal University, Guangzhou, China

  11. Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails

    Sep 27, 2026Gert Lek, Abele Malan, Chaoyi Zhu +3LLM Safety BenchmarksLLM Guardrails

    University of Neuchâtel · Delft University of Technology · IBM Research +1

  12. Baszta: Data-Centric Fine-Tuning of a Polish Multi-Label Safety Classifier

    Sep 24, 2026Adam Górski, Mateusz Jąkalak, Rafał JakubowskiMulti-Label ClassificationLanguage Model Safety Evaluation

    Billennium S.A.

  13. CrossSafe: Towards Cross-Embodiment Latent Safety Filters

    Sep 24, 2026Ihab Tabbara, Yuxuan Yang, Hussein SibaiReachability AnalysisCross-Embodiment Robot Learning

    Department of Computer Science and Engineering, Washington University in St. Louis, St. Louis, MO, USA

  14. LEAP-CBF: A Safety Filter for Uncertain Systems with Least-Effort Adversarial Potentials

    Sep 23, 2026Oswin So, Eric Yu, Chuchu FanSafety-Critical ControlControl Barrier Functions

    Massachusetts Institute of Technology.

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

    Sep 23, 2026Zeyu Wang, Xiaodan Li, Zhiwen Li +2T2I GenerationSafe T2I Generation

    Alibaba AAIG

  16. Turning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement Learning

    Sep 23, 2026Ruihan Wu, Rui Yang, Donggeon David Oh +2Sequential MARLRL for Robotics

    Department of Computer Science, Johns Hopkins University, Baltimore, MD 21218, USA · Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544, USA

  17. Can Data Attribution Filter Out Subliminal Learning? Not Reliably

    Sep 17, 2026Moritz Weckbecker, Sweta Jena, Jonas Müller +5Gradient-Based AttributionTraining Data Curation

    Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute · International Institute of Information Technology Hyderabad · Department of Electrical Engineering and Computer Science, Technische Universität Berlin +4

  18. Runtime Safety Filtering for Two-Terminal Hazards in Robotic Battery Recycling

    Sep 17, 2026Yuxin Cao, Wei Song, Xianglin Yang +4Robot SafetySafety Filtering

    National University of Singapore, Singapore · Griffith University, Australia · UNSW Canberra, Australia +2

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

    Sep 16, 2026Alizishaan Khatri, Chiquita Prabhu, Omkar NeogiSafety FilteringLLM Safety

    Wrynx Inc. · Independent Researcher

  20. Winning a Won Game: Strict Reach-Avoid-Stay Control Barrier Functions for High-Dimensional Black-Box Systems

    Sep 16, 2026Donggeon David Oh, Duy P. Nguyen, Gongkai Yuan +3Robotic ControlControl Barrier Functions

    Department of Computer Science, Johns Hopkins University, Baltimore, MD 21218, USA

  21. Timely Activation of Safety Filters via One-Step Reachability Expansion

    Sep 15, 2026Javier BorquezReachability AnalysisSafety-Critical Control

    Universidad de Santiago de Chile Santiago, Chile

  22. ResSafe: Learning Safety Filtering with Residual Reinforcement Learning for Humanoids

    Sep 14, 2026Gechen Qu, Tong Zhang, Bike Zhang +4Safety-Critical ControlHumanoid Robot Control

    University of California, Berkeley · University of California, Los Angeles

  23. Certified Safety Curation: Distribution-Free Guarantees for Safe Offline Reinforcement Learning

    Sep 14, 2026Adam Haroon, Cody FlemingOffline RLSafety Filtering

    Iowa State University Ames, IA, USA

  24. Exact Feasibility Certification and Optimal Responsibility Allocation for Multi-Robot CBF Safety Filters

    Sep 14, 2026Chandan Kumar Sah, Jishnu KeshavanSafety-Critical ControlControl Barrier Functions

    Department of Mechanical Engineering, Indian Institute of Science, Bengaluru 560012, India

  25. CS-Guard: Benchmarking LLM Guardrails for Code Generation Security

    Sep 9, 2026Jinyang Li, Mingyu Guo, Hung X. NguyenLLM GuardrailsAdversarial Attacks on LLMs

    Adelaide University Adelaide, Australia

  26. Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts

    Sep 8, 2026Yongxi Zhou, Wenbo Ye, Yuanzhe Liu +2LLM Safety BenchmarksLLM-as-a-Judge

    Northeastern University, Massachusetts, USA · University of Southern California, California, USA · Georgia Institute of Technology, Georgia, USA

  27. Recall Is Not Protection: Evaluating Safety Monitors Against Model Compliance

    Sep 5, 2026Sripad KarneLanguage Model Safety EvaluationLLM Guardrails

    Columbia University

  28. Jailbreaking Text-to-Image Models Through Cracks: Navigating Heterogeneous Safety Filters via Multi-Agent Debate

    Sep 1, 2026Kaiyan Wen, Shijie Zhang, Lu Yu +1Adversarial Attacks on VLMsMulti-Agent Debate

    College of Computer Science and Technology, National University of Defense Technology, Changsha 410073, China · Shenzhen MSU-BIT University, Shenzhen, China · City University of Hong Kong, Hong Kong, China

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

    Sep 1, 2026Nikita Oblakov, Sabrina Sadiekh, Evgeniy KokuykinLanguage Model Safety EvaluationLLM Guardrails

    HiveTraceLab

  30. Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts

    Sep 1, 2026Rui Yang, Yang Hong, Yichao Xu +3LLM Safety BenchmarksLLM Refusal Behavior

    Johns Hopkins University

  31. 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 +3LLM GuardrailsLLM Agent Security

    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

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

    Aug 18, 2026Istiaque Ahmed, Afia Anjum Borsha, Ranat Das Prangon +2LLM GuardrailsAdversarial Attacks on LLMs

    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

  33. Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers

    Aug 14, 2026Thiago Sandoval, Ufuk TopcuDistribution ShiftSelective Prediction

    The University of Texas at Austin

  34. Robust Safety Filtering for Input-Constrained Underactuated Linear Systems

    Aug 11, 2026Muhamad Rausyan FikriSafety-Critical ControlControl Barrier Functions

    Faculty of Engineering and Natural Sciences, Tampere University, 33720 Tampere, Finland

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

    Aug 11, 2026Xinzhe Huang, Biwu Yao, Kedong Xiu +4LLM GuardrailsLanguage Model Calibration

    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

  36. Withholding the Completing Chunk: Deterministic Pair-Completion Guardrails for Streaming LLM Output

    Aug 10, 2026Christopher M. FrostLanguage Model Safety EvaluationLLM Guardrails

    HEOSSI (Pte.) Ltd., Singapore

  37. Measuring the Wrong Thing: Internal Harmfulness Scores Anti-Rank Successful Jailbreaks

    Aug 10, 2026Mingyu Luo, Ming Deng, Zilang Qiu +8Safety FilteringLLM Jailbreak Attacks

    College of Computer Science and Artificial Intelligence, Fudan University · School of Computer Engineering and Science, Shanghai University · Beijing Normal University +5

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

    Aug 9, 2026Cong Ming, Jingyi Chen, Bin Liu +4Continual Learning for LLMsLLM Guardrails

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

  39. NiyamAI - An Intent-Bound AI Agent with Cryptographically Verifiable Guardrails using Zero-Knowledge Proofs

    Aug 7, 2026Aditya Katkar, Om Karkele, Kartik Mandhane +2Tool-Augmented Language Model AgentsLLM Guardrails

    Department of Computer Engineering, Vishwakarma Institute of Technology, Pune, Maharashtra, India

  40. Social Pressure Breaks Majority Voting in LLM Safety Panels

    Aug 5, 2026Yibo Hu, Jiaming QuNormative Conformity in Language ModelsSafety Filtering

    Illinois Institute of Technology · Amazon

  41. When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models

    Aug 4, 2026Yu Feng, Chunting Zang, Chen Shen +4Language Model Safety EvaluationLLM Guardrails

    The University of Sydney · Alibaba Group · Jilin University +1

  42. Aligned in Form, Not in Meaning: The Comprehension - Containment Decoupling of LLM Safety in Low-Resource Bangla Derogatory Speech

    Aug 3, 2026Shadab Bin Habib, A K M Ferdous Reza Habib, Subarno Neel +1Language Model Safety EvaluationLLM Safety Alignment

    Department of Computer Science and Engineering Islamic University of Technology, Dhaka, Bangladesh

  43. Mind the Gap: Zero-Query Jailbreaks via Filter-Generator Discrepancy in Text-to-Image Systems

    Aug 2, 2026Wanguang Li, Zhaoxin Wang, Handing WangAdversarial Prompt GenerationT2I Generation

    School of Artificial Intelligence, Xidian University, Shaanxi, China

  44. Towards General Language-Conditioned Latent Safety Filters

    Jul 31, 2026Ihab Tabbara, Yuxuan Yang, Hussein SibaiRobotic ControlRobot Safety

    Department of Computer Science and Engineering, Washington University in St. Louis, MO 63130, USA

  45. Old Tricks, New Models: How Simple Image Transformations Break Modern AI-based Content Moderation

    Jul 30, 2026Marco Alecci, Francesco Marchiori, Iyiola Emmanuel Olatunji +2Multimodal RobustnessAdversarial Attacks

    Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg · Department of Mathematics, University of Padua, Padua, Italy

  46. Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs

    Jul 30, 2026Pingyu Wu, Lingyao Zhu, Weiming Zhang +1Adversarial Attacks on LLMsSafety Filtering

    University of Science and Technology of China · Hefei AiDA Lab · Zhejiang Wanli University

  47. RoguePrompt: Dual-Layer Encoding for Self-Reconstruction to Circumvent LLM Moderation

    Jul 29, 2026Benyamin Tafreshian, Prathamesh DhakeAdversarial AttacksAdversarial Attacks on LLMs

    Department of Computer Science · Boston University · Boston, MA, USA

  48. Attack Ensembles Expose a Safety-Utility Trade-off in Black-Box Guard Defenses Against Encoded VLM Jailbreaks

    Jul 29, 2026Haoyu Zhang, Zhuoxi Wang, Shibo Zheng +7VLM RobustnessAdversarial Attacks on VLMs

    Northeastern University

  49. Choosing Where and How to Moderate: End-to-End Trade-offs in Filter Placement and Response Rewriting

    Jul 28, 2026Mengya Hu, Susie Park, Suzana Ilic +5Language Model Safety EvaluationContent Moderation

    Microsoft Responsible AI · Goodfire

  50. Shieldstral

    Jul 28, 2026Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli +273Language Model Safety EvaluationContent Moderation

  51. Harm is not Universal: Community-Specific Toxicity Detection is Urgently Needed

    Jul 27, 2026Xinnuo Xu, Anja Thieme, Daniela Massiceti +6T2I GenerationSafe T2I Generation

    Microsoft Research Cambridge, UK · Microsoft Paris, France

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

    Jul 23, 2026Dongbin NaVLM EvaluationEfficient VLM Inference

    POSTECH

  53. SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing

    Jul 15, 2026Tianyu Chen, Chujia Hu, Wenjie WangLanguage Model Safety EvaluationLLM Guardrails

    ShanghaiTech University, Shanghai, China

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

    Jul 13, 2026SingGuard TeamLLM GuardrailsAI Agent Security

    AI Security Lab, Ant Group

  55. NetInjectBench: Benchmarking Indirect Prompt Injection in Tool-Using Large Language Model Agents for Network Operations

    Jul 11, 2026Ruksat Khan Shayoni, Muhammad Faraz Shoaib, S M Asif Hossain +1AI Agent Security BenchmarksIndirect Prompt Injection

    School of Computing, Wichita State University, Kansas, USA · Department of Computer Science, American International University-Bangladesh, Dhaka, Bangladesh

  56. Runtime Safety Filtering for Learned Small UAS Separation Policies under GNSS Degradation

    Jul 10, 2026Alex Zongo, Peng WeiCollision AvoidanceSafety Filtering

    Department of Mechanical and Aerospace Engineering · George Washington University · Washington, D.C., USA

  57. DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail

    Jul 7, 2026He Liu, Changtao Miao, Xinjie Yang +12Reasoning DistillationLLM Guardrails

    Ant Digital Technologies, Ant Group

  58. Evaluating calibrated refusal and safe usefulness in dual-use biology settings

    Jul 6, 2026Edwin H. Wintermute, Harmon Bhasin, Christina M. Agapakis +13LLM Refusal BehaviorSafety Filtering

    American Wetware, Boston, MA · LatchBio, San Francisco, CA

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

    Jul 2, 2026William Hackett, Peter GarraghanLLM AuditingLLM Guardrails

    Mindgard · Lancaster University

  60. HaloGuard 1.0: An Open Weights Constitutional Classifier for Multilingual AI Safety

    Jul 2, 2026Navaneeth Sangameswaran, Preetham S, Ashmiya LeninLLM Safety BenchmarksLanguage Model Safety Evaluation

    Astroware AI, Delaware, USA · Karunya Institute of Technology and Sciences, Coimbatore, India