JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
by Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko and colleagues
Learn why jailbreak studies need consistent threat models, scoring and reproducible comparisons.
JailbreakBench proposes a standardized framework for comparing language-model jailbreak attacks and defenses. The paper explains reproducibility and evaluation conventions; this index links the research without reproducing attack prompts.
- Level
- Advanced
- Models
- model-agnostic
- Category
- Jailbreaking and red teaming
- Tags
- primary-source, jailbreak-research
- Source date
- 2024-03-28
- Added
- 2026-10-18
- Last verified
- 2026-10-18
- Status
- ok
- Prerequisites
- Assumes knowledge of LLM safety evaluation, threat models and experimental comparisons.
- Subcategory
- jailbreak research
- Region
- West
- Original language
- en
- Access
- free
- Resource reuse
- closed: The inspected paper states the arXiv perpetual non-exclusive distribution license, not a general open-reuse grant. The benchmark code’s separate license is not transferred to this linked paper. Facet definitions
Summary in our own words. Rights remain with the original creator. Credit and correction policy.