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

45 papers2 papers in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

  1. Jailbreak Detection on Large Language Models via Contrastive Prototype Structures

    Nov 18, 2026Yan Qiu, Yuanyuan LiJailbreak DetectionLLM Safety Monitoring

  2. Beyond AUROC: Deployment-Aware Evaluation of Model-Internal Jailbreak Detectors

    Nov 8, 2026Mohammad Tehabsim, Basil Al-Housani, Nour Alhussien +1Jailbreak DetectionLanguage Model Safety Evaluation

  3. Beyond the Prompt: Leveraging Pre-Decoding States for Jailbreak Detection in dLLMs

    Nov 6, 2026Adam Hazimeh, Amel Abdelraheem, Ke Wang +4Jailbreak DetectionLLM Safety Monitoring

  4. Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge

    Oct 5, 2026Wonjun Lee, Kyungsik Yang, Gaeun Ji +5Adversarial Attacks on LLMsLLM Security

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

    Oct 2, 2026Omanshu ThapliyalCertified RobustnessState Space Models

  6. Why Jailbreaks Succeed in Diffusion Language Models: An Energy Landscape Analysis

    Sep 25, 2026Thong Bach, Dung Nguyen, Thao Minh Le +1Jailbreak DetectionLLM Safety

  7. Harmfulness Propagation Dynamics: Layer-wise Trajectories of Adversarial Intent in Large Language Models

    Sep 11, 2026Noor Islam S. Mohammad, Uluğ BayazıtJailbreak DetectionLLM Security

  8. SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis and Fluency Measurement

    Sep 5, 2026Quoc Viet Vo, Trung Le, Damith C. Ranasinghe +1Jailbreak DetectionLLM Security

  9. 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

  10. 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

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

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

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

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

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

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

  14. 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

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

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

  16. 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

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

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

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

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

  19. Re-Triggering Safeguards within LLMs for Jailbreak Detection

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