ML Security PapersSoK: Taxonomy and Evaluation of Prompt Security in Large Language Models
Hanbin Hong, Shuya Feng, Nima Naderloui et al. · University of Connecticut · University of Alabama at Birmingham
SoK survey unifying LLM jailbreak taxonomy, threat models, evaluation toolkit, and the largest annotated jailbreak dataset
Large Language Models (LLMs) have rapidly become integral to real-world applications, powering services across diverse sectors. However, their widespread deployment has exposed critical security risks, particularly through jailbreak prompts that can bypass model alignment and induce harmful outputs. Despite intense research into both attack and defense techniques, the field remains fragmented: definitions, threat models, and evaluation criteria vary widely, impeding systematic progress and fair comparison. In this Systematization of Knowledge (SoK), we address these challenges by (1) proposing a holistic, multi-level taxonomy that organizes attacks, defenses, and vulnerabilities in LLM prompt security; (2) formalizing threat models and cost assumptions into machine-readable profiles for reproducible evaluation; (3) introducing an open-source evaluation toolkit for standardized, auditable comparison of attacks and defenses; (4) releasing JAILBREAKDB, the largest annotated dataset of jailbreak and benign prompts to date;\footnote{The dataset is released at \href{https://huggingface.co/datasets/youbin2014/JailbreakDB}{\textcolor{purple}{https://huggingface.co/datasets/youbin2014/JailbreakDB}}.} and (5) presenting a comprehensive evaluation platform and leaderboard of state-of-the-art methods \footnote{will be released soon.}. Our work unifies fragmented research, provides rigorous foundations for future studies, and supports the development of robust, trustworthy LLMs suitable for high-stakes deployment.