mlsanityData to 7 Oct 2026

MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots

arXiv 2307.08715 ↗First posted 16 Jul 2023cs.CRcited by 172

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Large Language Models (LLMs) have revolutionized Artificial Intelligence (AI) services due to their exceptional proficiency in understanding and generating human-like text. LLM chatbots, in particular, have seen widespread adoption, transforming human-machine interactions. However, these LLM chatbots are susceptible to "jailbreak" attacks, where malicious users manipulate prompts to elicit inappropriate or sensitive responses, contravening service policies. Despite existing attempts to mitigate such threats, our research reveals a substantial gap in our understanding of these vulnerabilities, largely due to the undisclosed defensive measures implemented by LLM service providers. In this paper, we present Jailbreaker, a comprehensive framework that offers an in-depth understanding of jailbreak attacks and countermeasures. Our work makes a dual contribution. First, we propose an innovative methodology inspired by time-based SQL injection techniques to reverse-engineer the defensive strategies of prominent LLM chatbots, such as ChatGPT, Bard, and Bing Chat. This time-sensitive approach uncovers intricate details about these services' defenses, facilitating a proof-of-concept attack that successfully bypasses their mechanisms. Second, we introduce an automatic generation method for jailbreak prompts. Leveraging a fine-tuned LLM, we validate the potential of automated jailbreak generation across various commercial LLM chatbots. Our method achieves a promising average success rate of 21.58%, significantly outperforming the effectiveness of existing techniques. We have responsibly disclosed our findings to the concerned service providers, underscoring the urgent need for more robust defenses. Jailbreaker thus marks a significant step towards understanding and mitigating jailbreak threats in the realm of LLM chatbots.

Key facts. Cited by 172 papers in the map (data through 7 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. First posted on arXiv 16 Jul 2023.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 9; 2024: 68; 2025: 63; 2026: 32.

172 papers.

Sort:

By area:

  1. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,326
  2. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMscited by 533
  3. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 380
  4. 2024A StrongREJECT for Empty Jailbreakscited by 352
  5. 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agentscited by 268
  6. 2024PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Modelscited by 251
  7. 2023Large Language Model Alignment: A Surveycited by 241
  8. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  9. 2024Optimization-based Prompt Injection Attack to LLM-as-a-Judgecited by 123
  10. 2023Mechanistically analyzing the effects of fine-tuning on procedurally defined taskscited by 110
  11. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  12. 2023AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Modelscited by 102
38 more
  1. 2024Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstructioncited by 95
  2. 2024Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documentscited by 93
  3. 2024Red-Teaming for Generative AI: Silver Bullet or Security Theater?cited by 81
  4. 2024Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editingcited by 77
  5. 2024FlipAttack: Jailbreak LLMs via Flippingcited by 73
  6. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
  7. 2024When LLMs Meet Cybersecurity: A Systematic Literature Reviewcited by 70
  8. 2024Large Language Models for Cyber Security: A Systematic Literature Reviewcited by 65
  9. 2023Jailbreaking GPT-4V via Self-Adversarial Attacks with System Promptscited by 62
  10. 2024SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Mannercited by 57
  11. 2024Multi-Turn Context Jailbreak Attack on Large Language Models From First Principlescited by 54
  12. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  13. 2024Don't Say No: Jailbreaking LLM by Suppressing Refusalcited by 53
  14. 2023Privacy in Large Language Models: Attacks, Defenses and Future Directionscited by 48
  15. 2024ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluationcited by 46
  16. 2024Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applicationscited by 36
  17. 2024Threats, Attacks, and Defenses in Machine Unlearning: A Surveycited by 34
  18. 2024Jailbreaking and Mitigation of Vulnerabilities in Large Language Modelscited by 33
  19. 2025Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Modelscited by 33
  20. 2025Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Modelscited by 32
  21. 2024AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulationcited by 31
  22. 2023Prompt Packer: Deceiving LLMs through Compositional Instruction with Hidden Attackscited by 30
  23. 2025VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Frameworkcited by 30
  24. 2024JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Modelscited by 28
  25. 2024BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attackscited by 28
  26. 2024Glitch Tokens in Large Language Models: Categorization Taxonomy and Effective Detectioncited by 27
  27. 2024Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Modelscited by 24
  28. 2024Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Modelscited by 23
  29. 2024SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Modelscited by 22
  30. 2024When LLMs Go Online: The Emerging Threat of Web-Enabled LLMscited by 22
  31. 2024Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Datacited by 21
  32. 2024Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Modelscited by 21
  33. 2024PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMscited by 20
  34. 2025From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoringcited by 20
  35. 2025NeuroStrike: Neuron-Level Attacks on Aligned LLMscited by 18
  36. 2024Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Modelscited by 17
  37. 2024Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testingcited by 17
  38. 2024PROMPTFUZZ: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMscited by 17

50 most cited of 172 All 172 (JSON)