mlsanityData to 14 Oct 2026

EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models

arXiv 2403.12171 ↗First posted 18 Mar 2024cs.CL cs.AIcited by 60

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Jailbreak attacks are crucial for identifying and mitigating the security vulnerabilities of Large Language Models (LLMs). They are designed to bypass safeguards and elicit prohibited outputs. However, due to significant differences among various jailbreak methods, there is no standard implementation framework available for the community, which limits comprehensive security evaluations. This paper introduces EasyJailbreak, a unified framework simplifying the construction and evaluation of jailbreak attacks against LLMs. It builds jailbreak attacks using four components: Selector, Mutator, Constraint, and Evaluator. This modular framework enables researchers to easily construct attacks from combinations of novel and existing components. So far, EasyJailbreak supports 11 distinct jailbreak methods and facilitates the security validation of a broad spectrum of LLMs. Our validation across 10 distinct LLMs reveals a significant vulnerability, with an average breach probability of 60% under various jailbreaking attacks. Notably, even advanced models like GPT-3.5-Turbo and GPT-4 exhibit average Attack Success Rates (ASR) of 57% and 33%, respectively. We have released a wealth of resources for researchers, including a web platform, PyPI published package, screencast video, and experimental outputs.

Key facts. Cited by 60 papers in the map (data through 14 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 22 of its 35 references that are in the map. First posted on arXiv 18 Mar 2024.

Builds on

22 of 35 references.

Closest ancestors · 12

Same direction, newest first

  1. 2024Fast Adversarial Attacks on Language Models In One GPU Minute23 Feb
  2. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs12 Jan
  3. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automatically4 Dec
  4. 2023A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily14 Nov
  5. 2023DeepInception: Hypnotize Large Language Model to Be Jailbreaker6 Nov
  6. 2023Jailbreaking Black Box Large Language Models in Twenty Queries12 Oct
  7. 2023Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations10 Oct
  8. 2023SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks5 Oct
  9. 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts19 Sep
  10. 2023Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM18 Sep
  11. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher12 Aug
  12. 2023Jailbroken: How Does LLM Safety Training Fail?5 Jul

Other references · 10

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2023Qwen Technical Reportcited by 3,344
  5. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,031
  6. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 651
  7. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 333
  8. 2023Shadow Alignment: The Ease of Subverting Safely-Aligned Language Modelscited by 297
  9. 2023Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Modelscited by 273
  10. 2023LLM Self Defense: By Self Examination, LLMs Know They Are Being Trickedcited by 244

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 23; 2025: 22; 2026: 15.

60 papers.

Sort:

By area:

  1. 2024Jailbreak Attacks and Defenses Against Large Language Models: A Surveycited by 230
  2. 2024Improved Techniques for Optimization-Based Jailbreaking on Large Language Modelscited by 110
  3. 2024Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editingcited by 79
  4. 2024Safeguarding Large Language Models: A Surveycited by 78
  5. 2024JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Modelscited by 70
  6. 2025Safety at Scale: A Comprehensive Survey of Large Model and Agent Safetycited by 67
  7. 2024SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Typescited by 60
  8. 2024Learn Your Reference Model for Real Good Alignmentcited by 57
  9. 2024JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Modelscited by 31
  10. 2025100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Modelscited by 30
  11. 2024Protecting Your LLMs with Information Bottleneckcited by 29
  12. 2024No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attackscited by 29
38 more
  1. 2025The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMscited by 26
  2. 2024h4rm3l: A language for Composable Jailbreak Attack Synthesiscited by 24
  3. 2025SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignmentcited by 24
  4. 2024Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detectioncited by 23
  5. 2024Can Editing LLMs Inject Harm?cited by 22
  6. 2024The Better Angels of Machine Personality: How Personality Relates to LLM Safetycited by 21
  7. 2026OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMscited by 21
  8. 2024Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAIcited by 16
  9. 2024AutoJailbreak: Exploring Jailbreak Attacks and Defenses through a Dependency Lenscited by 14
  10. 2026Autonomous Agents on Blockchains: Standards, Execution Models, and Trust Boundariescited by 13
  11. 2025Think Twice, Generate Once: Safeguarding by Progressive Self-Reflectioncited by 11
  12. 2025Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMscited by 9
  13. 2024Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attackscited by 8
  14. 2025PiCo: Jailbreaking Multimodal Large Language Models via Pictorial Code Contextualizationcited by 8
  15. 2025Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMscited by 8
  16. 2025Towards the Worst-case Robustness of Large Language Modelscited by 7
  17. 2025TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluationscited by 7
  18. 2024EnJa: Ensemble Jailbreak on Large Language Modelscited by 5
  19. 2024BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Modelscited by 5
  20. 2025SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defensescited by 5
  21. 2024RogueGPT: dis-ethical tuning transforms ChatGPT4 into a Rogue AI in 158 Wordscited by 4
  22. 2025PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attackscited by 4
  23. 2025Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Modelscited by 4
  24. 2025IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinementcited by 4
  25. 2025PLAGUE: Plug-and-play framework for Lifelong Adaptive Generation of Multi-turn Exploitscited by 3
  26. 2025LM-Fix: Lightweight Bit-Flip Detection and Rapid Recovery Framework for Language Modelscited by 3
  27. 2026SoK: Robustness in Large Language Models against Jailbreak Attackscited by 3
  28. 2026MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attackscited by 3
  29. 2024Gen-AI for User Safety: A Surveycited by 2
  30. 2025LoRA Users Beware: A Few Spurious Tokens Can Manipulate Your Finetuned Modelcited by 2
  31. 2026Cybersecurity is the True Frontier for Generative AI Success or Failurecited by 2
  32. 2024Position: Towards Resilience Against Adversarial Examplescited by 1
  33. 2025SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Modelscited by 1
  34. 2025AutoRed: A Free-form Adversarial Prompt Generation Framework for Automated Red Teamingcited by 1
  35. 2025VisualDAN: Exposing Vulnerabilities in VLMs with Visual-Driven DAN Commandscited by 1
  36. 2026AJAR: Adaptive Jailbreak Architecture for Red-teamingcited by 1
  37. 2026SafeThinker: Reasoning about Risk to Deepen Safety Beyond Shallow Alignmentcited by 1
  38. 2026NAAMSE: Framework for Evolutionary Security Evaluation of Agentscited by 1

50 most cited of 60 All 60 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models
  2. 2025GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing
  3. 2026ShallowJail: Steering Jailbreaks against Large Language Models
  4. 2024A Cross-Language Investigation into Jailbreak Attacks in Large Language Models
  5. 2024Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks
  6. 2024Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
  7. 2024Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models
  8. 2024Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks