# Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning

arXiv: https://arxiv.org/abs/2509.23558 · HTML: https://mlsanity.com/paper/2509.23558/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 19 of its 23 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs](https://mlsanity.com/paper/2402.11753/) (2024)
- [Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction](https://mlsanity.com/paper/2402.18104/) (2024)
- [FlipAttack: Jailbreak LLMs via Flipping](https://mlsanity.com/paper/2410.02832/) (2024)
- [RL-JACK: Reinforcement Learning-powered Black-box Jailbreaking Attack against LLMs](https://mlsanity.com/paper/2406.08725/) (2024)
- [SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage](https://mlsanity.com/paper/2412.15289/) (2024)

## Built on by (most cited first, 2 of 2)

- [A Systematic Investigation of RL-Jailbreaking in LLMs](https://mlsanity.com/paper/2605.07032/) (2026)
- [Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution](https://mlsanity.com/paper/2605.13411/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable capabilities, yet they also introduce novel security challenges. For instance, prompt jailbreaking attacks involve adversaries crafting sophisticated prompts to elicit responses from LLMs that deviate from human values. To uncover vulnerabilities in LLM alignment methods, we propose the PASS framework (underlinePrompt Junderlineailbreaking via underlineSemantic and underlineStructural Formalization). Specifically, PASS employs reinforcement learning to transform initial jailbreak prompts into formalized descriptions, which enhances stealthiness and enables bypassing existing alignment defenses. The jailbreak outputs are then structured into a GraphRAG system that, by leveraging extracted relevant terms and formalized symbols as contextual input alongside the original query, strengthens subsequent attacks and facilitates more effective jailbreaks. We conducted extensive experiments on common open-source models, demonstrating the effectiveness of our attack.