mlsanityData to 7 Oct 2026

JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models

arXiv 2404.08793 ↗First posted 12 Apr 2024cs.CR cs.CL cs.HCcited by 7

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

The proliferation of large language models (LLMs) has underscored concerns regarding their security vulnerabilities, notably against jailbreak attacks, where adversaries design jailbreak prompts to circumvent safety mechanisms for potential misuse. Addressing these concerns necessitates a comprehensive analysis of jailbreak prompts to evaluate LLMs' defensive capabilities and identify potential weaknesses. However, the complexity of evaluating jailbreak performance and understanding prompt characteristics makes this analysis laborious. We collaborate with domain experts to characterize problems and propose an LLM-assisted framework to streamline the analysis process. It provides automatic jailbreak assessment to facilitate performance evaluation and support analysis of components and keywords in prompts. Based on the framework, we design JailbreakLens, a visual analysis system that enables users to explore the jailbreak performance against the target model, conduct multi-level analysis of prompt characteristics, and refine prompt instances to verify findings. Through a case study, technical evaluations, and expert interviews, we demonstrate our system's effectiveness in helping users evaluate model security and identify model weaknesses.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 66 of its 95 references that are in the map. First posted on arXiv 12 Apr 2024.

Builds on

66 of 95 references.

Closest ancestors · 13

Same direction, newest first

  1. 2024Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs21 Feb
  2. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs12 Jan
  3. 2023A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily14 Nov
  4. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks16 Oct
  5. 2023Jailbreaking Black Box Large Language Models in Twenty Queries12 Oct
  6. 2023AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models3 Oct
  7. 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts19 Sep
  8. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher12 Aug
  9. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models7 Aug
  10. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
  11. 2023MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots16 Jul
  12. 2023Jailbroken: How Does LLM Safety Training Fail?5 Jul
1 more
  1. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study23 May

Other references · 53

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2022Training language models to follow instructions with human feedbackcited by 15,712
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  6. 2023Visual Instruction Tuningcited by 7,792
  7. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  8. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  9. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  10. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,330
  11. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  12. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
38 more
  1. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 979
  2. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 760
  3. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
  4. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 320
  5. 2023Visual Adversarial Examples Jailbreak Aligned Large Language Modelscited by 307
  6. 2023Are aligned neural networks adversarially aligned?cited by 305
  7. 2023Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attackscited by 268
  8. 2023Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Modelscited by 260
  9. 2019The What-If Tool: Interactive Probing of Machine Learning Modelscited by 207
  10. 2015Visualizing and Understanding Neural Models in NLPcited by 199
  11. 2015Visualizing and Understanding Recurrent Networkscited by 158
  12. 2023OpenAgents: An Open Platform for Language Agents in the Wildcited by 136
  13. 2024Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agentscited by 135
  14. 2023Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicitycited by 86
  15. 2023Safety Assessment of Chinese Large Language Modelscited by 82
  16. 2022Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Modelscited by 70
  17. 2019explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learningcited by 69
  18. 2023Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Modelscited by 67
  19. 2023Graphologue: Exploring Large Language Model Responses with Interactive Diagramscited by 65
  20. 2023Composite Backdoor Attacks Against Large Language Modelscited by 63
  21. 2022Adversarial Training for High-Stakes Reliabilitycited by 60
  22. 2023PromptMagician: Interactive Prompt Engineering for Text-to-Image Creationcited by 58
  23. 2023AttentionViz: A Global View of Transformer Attentioncited by 50
  24. 2023"What It Wants Me To Say": Bridging the Abstraction Gap Between End-User Programmers and Code-Generating Large Language Modelscited by 48
  25. 2023Sensecape: Enabling Multilevel Exploration and Sensemaking with Large Language Modelscited by 48
  26. 2017Understanding Hidden Memories of Recurrent Neural Networkscited by 43
  27. 2024Navigating the OverKill in Large Language Modelscited by 40
  28. 2020DECE: Decision Explorer with Counterfactual Explanations for Machine Learning Modelscited by 38
  29. 2022MultiViz: Towards Visualizing and Understanding Multimodal Modelscited by 36
  30. 2020Analyzing the Noise Robustness of Deep Neural Networkscited by 31
  31. 2023Spellburst: A Node-based Interface for Exploratory Creative Coding with Natural Language Promptscited by 30
  32. 2021Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behaviorcited by 29
  33. 2019Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analyticscited by 23
  34. 2024AgentLens: Visual Analysis for Agent Behaviors in LLM-based Autonomous Systemscited by 23
  35. 2022A Unified Understanding of Deep NLP Models for Text Classificationcited by 18
  36. 2023XNLI: Explaining and Diagnosing NLI-based Visual Data Analysiscited by 18
  37. 2020Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networkscited by 12
  38. 2023Storyfier: Exploring Vocabulary Learning Support with Text Generation Modelscited by 12

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 5.

7 papers.

  1. 2024Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMscited by 47
  2. 2024Adversarial Tuning: Defending Against Jailbreak Attacks for LLMscited by 23
  3. 2025"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Modelscited by 7
  4. 2025XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented Generationcited by 2
  5. 2025Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformerscited by 2
  6. 2025JaiLIP: Jailbreaking Vision-Language Models via Loss Guided Image Perturbationcited by 2
  7. 2025NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Modelscited by 1