Jailbreak Detection

Ask about this topic

Overview

Jailbreak detection studies how to recognize malicious or policy-evading inputs before a model complies, including attacks hidden in long conversations, other languages, images, or obfuscated text. Approaches range from compact classifiers using lexical and semantic features to runtime monitors that inspect hidden states, token entropy, refusal signals, or output logits; some track risk across turns or combine multiple detectors. The field is expanding from prompt-only checks toward multilingual, multimodal, and decoding-time detection, with attention to latency and deployment cost. A central challenge is maintaining high recall at very low false-positive rates when attacks and benign inputs differ from training data, especially under adaptive attacks and realistic conversation distributions.

Latest papers

CardsList

36 papers3 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

  1. Bounded Reachability & Jailbreak Detection via Contraction-Constrained State Space Models

    Oct 2, 2026Omanshu ThapliyalCertified RobustnessState Space Models

    Strategic Data Solutions Lab, Hitachi America Ltd. Santa Clara, CA 94086, USA

  2. Prompted to Discriminate: Generalizing Malicious-Input Probes in the Wild

    Oct 1, 2026Elad David, Max FominPrompt Injection DetectionLanguage Model Probing

    Zenity Tel Aviv, Israel

  3. Does the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue

    Sep 29, 2026Omar Sheta, Rinku Deuja, Hadi Masoudi +1Language Model Safety EvaluationAdversarial Attacks on LLMs

    University of Louisville Louisville, Kentucky, USA

  4. Monitor Jailbreaking: Evading Chain-of-Thought Monitoring Without Encoded Reasoning

    Sep 25, 2026Julian SchulzCoT MonitoringLanguage Model Safety Evaluation

    Meridian Cambridge

  5. An Empirical Measurement of Jailbreaking Evaluators

    Sep 7, 2026Yujie MuJailbreak Attack EvaluationAutomated Evaluation

    Independent Researcher

  6. 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

  7. 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

  8. Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models

    Jun 26, 2026Yanchen Yin, Dongqi Han, Linghui LiAttention Head AnalysisJailbreak Attacks

    Beijing University of Posts and Telecommunications, Beijing, China.

  9. What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics

    Jun 23, 2026Sofiia Nikolenko, Michele Papucci, Mina Rezaei +1LLM InterpretabilityLLM Jailbreak Attacks

    LMU Munich, Munich, Germany · relAI – Konrad Zuse School of Excellence in Reliable AI · University of Pisa, Pisa, Italy +2

  10. Scalable Hierarchical Attention Transformers for Multi-Turn Jailbreak Detection in Long Conversations

    Jun 19, 2026Chenhui Hu, Muhammed Salih, Sudipto Guha +1TransformerMulti-Turn Jailbreak Attacks

    Zscaler, Inc.

  11. Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework

    Jun 15, 2026David Huang, Jaewon Chang, Avidan Shah +2LLM Backdoor AttacksPrompt Injection Attacks

    Princeton University · Anthropic · UC Berkeley +2

  12. BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems

    Jun 12, 2026Leonhard Waibl, Felix Michalak, Hadrien MariacciaLLM Safety BenchmarksLLM Guardrails

    University of Graz, Graz, Austria · Supervised Program for Alignment Research (SPAR) · Centre pour la Sécurité de l’IA (CeSIA), Paris, France.

  13. GuardNet: Ensemble Strategies of Shallow Neural Networks for Robust Prompt Injection and Jailbreak Detection

    Jun 4, 2026Paulo Ricardo Ferreira Neves, Edson Rodrigues da Cruz Filho, Paulo Henrique Eleuterio Falsetti +7LLM GuardrailsNeural Network Robustness

    Quickium Technology Ltd. – Piracicaba, São Paulo · Federal Institute of Education, Science and Technology of São Paulo (IFSP) – Piracicaba Campus – São Paulo · Federal University of São Carlos (UFSCar) – Sorocaba Campus – São Paulo

  14. Gate AI: LLM Security Benchmark Evaluation Methodology and Results

    Jun 1, 2026Ryle Goehausen, Marcus SousaLLM Safety BenchmarksLanguage Model Safety Evaluation

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

    May 28, 2026Ihor Stepanov, Aleksandr SmechovLanguage Model Safety EvaluationLLM Guardrails

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

  16. Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures

    May 28, 2026Junyoung Park, Sunghwan Park, Seongyong Ju +1LLM Safety EvaluationLLM Jailbreak Attacks

    Chung-Ang University

  17. Evolving and Detecting Multi-Turn Deception using Geometric Signatures

    May 26, 2026Surender Suresh Kumar, Mary L. CummingsAdversarial Prompt GenerationDeception in Language Models

    George Mason University Fairfax, USA

  18. Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models

    May 26, 2026Hayden Helm, Xiaodong Liu, Weiwei YangJailbreak RobustnessJailbreak Detection

    Helivan · Microsoft Research

  19. Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection

    May 24, 2026Lixing Lin, Juli You, Yue Li +4Language Model Safety EvaluationLLM Guardrails

    yaleYale University, New Haven, CT, USA · indIndependent Researcher · columbiaColumbia University, New York, NY, USA +2

  20. Detecting Fluent Optimization-Based Adversarial Prompts via Sequential Entropy Changes

    May 19, 2026Mohammed Alshaalan, Miguel R. D. RodriguesAdversarial Attacks on LLMsJailbreak Detection

    Department of Electronic and Electrical Engineering, University College London, London, United Kingdom.

  21. Exploring and Developing a Pre-Model Safeguard with Draft Models

    May 19, 2026Hongyu Cai, Arjun Arunasalam, Yiming Liang +2LLM GuardrailsSafety Filtering

    Purdue University West Lafayette, Indiana, USA · Florida International University Miami, Florida, USA

  22. Before the Last Token: Diagnosing Final-Token Safety Probe Failures

    May 12, 2026Shravan DodaLanguage Model Safety EvaluationSafety Filtering

    Kipo AI

  23. Re-Triggering Safeguards within LLMs for Jailbreak Detection

    May 11, 2026Zheng Lin, Zhenxing Niu, Haoxuan Ji +2LLM Jailbreak AttacksJailbreak Detection

    1Xidian University · 2Xi’an Jiaotong University

  24. GLiGuard: Schema-Conditioned Classification for LLM Safeguard

    May 8, 2026Urchade Zaratiana, Mary Newhauser, George Hurn-Maloney +1Jailbreak DefenseText Classification

    Fastino Labs

  25. Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection

    May 2, 2026Xulin Hu, Che Wang, Wei Yang Bryan Lim +2Adversarial Attacks on LLMsLLM Refusal Behavior

    1Peking University · 2Nanyang Technological University · 3Beijing Jiaotong University

  26. TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning

    Apr 30, 2026Bowen Sun, Chaozhuo Li, Yaodong Yang +2Jailbreak AttacksLLM Security

    Johns Hopkins University · Microsoft Research Asia · Peking University +1

  27. Cross-Lingual Jailbreak Detection via Semantic Codebooks

    Apr 28, 2026Shirin Alanova, Bogdan Minko, Sabrina Sadiekh +1Multilingual Language Model EvaluationLLM Security

    AI Talent Hub, ITMO University · HiveTraceLab

  28. Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models

    Apr 27, 2026Nay Myat Min, Long H. Pham, Jun SunLLM Backdoor AttacksAdversarial Attacks on LLMs

    Singapore Management University

  29. One Jailbreak, Many Tongues: Learning Language-Insensitive Intention Representations for Multilingual Jailbreak Detection

    Apr 22, 2026Shuyu Jiang, Kaiyu Xu, Xingshu Chen +5Multilingual Language ModelsBack-Translation

    School of Cyber Science and Engineering, Sichuan University, Chengdu, 610065, China · School of Computer Science and Engineering, Nanyang Technological University · School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China

  30. An Empirical Study of Multi-Generation Sampling for Jailbreak Detection in Large Language Models

    Apr 20, 2026Hanrui Luo, Shreyank N GowdaLanguage Model Safety EvaluationLLM Auditing

    School of Computer Science, University of Nottingham, Nottingham, United Kingdom.