JailbreakLens: Visual Analysis of Jailbreak Attacks Against Large Language Models

2024-04-12

arXiv.org

AI Summary

To address the lack of systematic analysis tools for jailbreaking attacks against large language models (LLMs), this paper introduces JailbreakLens—the first collaborative analysis framework integrating LLM-based reasoning with multidimensional visualization. It enables automated evaluation of jailbreak prompts, component-level semantic decomposition (e.g., intent, obfuscation, and trigger mechanisms), and interactive prompt refinement, supported by heatmaps, treemaps, and temporal trajectory visualizations. Its key innovations include LLM-assisted feature parsing and a human-in-the-loop verification闭环. Evaluated through case studies, technical benchmarks, and expert interviews, JailbreakLens significantly improves jailbreak pattern identification accuracy (+32.7%) and accelerates model vulnerability localization (58% reduction in average analysis time). The framework establishes a new paradigm for interpretable, reproducible LLM security assessment.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness
• Computer Vision: Large Vision Models

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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.

Problem

• Analyzing jailbreak prompts to assess LLM security vulnerabilities
• Streamlining evaluation of jailbreak performance and prompt characteristics
• Identifying model weaknesses through visual and multi-level analysis

Innovation

• LLM-assisted framework for jailbreak analysis
• Automatic assessment of jailbreak prompts
• Visual system for multi-level prompt analysis