Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks
Document Type
Conference Proceeding
Publication Title
2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings
Abstract
Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive outputs, and violations of content regulator policies. Limited studies have been conducted to formalize and analyze these attacks and their mitigations. We bridge this gap by proposing a formalism and a taxonomy of known (and possible) jailbreaks. We survey existing jailbreak methods and their effectiveness on open-source and commercial LLMs (such as GPT-based models, OPT, BLOOM, and FLAN-T5-XXL). We further discuss the challenges of jailbreak detection in terms of their effectiveness against known attacks. For further analysis, we release a dataset of model outputs across 3700 jailbreak prompts over 4 tasks.
First Page
16802
Last Page
16830
Publication Date
1-1-2024
Recommended Citation
A. Rao et al., "Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks," 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings, pp. 16802 - 16830, Jan 2024.