# JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs

arXiv: https://arxiv.org/abs/2412.15623 · HTML: https://mlsanity.com/paper/2412.15623/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 20 Dec 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)
- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 23 of 23)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study](https://mlsanity.com/paper/2305.13860/) (2023)
- [Detecting Language Model Attacks with Perplexity](https://mlsanity.com/paper/2308.14132/) (2023)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [Multi-step Jailbreaking Privacy Attacks on ChatGPT](https://mlsanity.com/paper/2304.05197/) (2023)
- [Low-Resource Languages Jailbreak GPT-4](https://mlsanity.com/paper/2310.02446/) (2023)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [Jailbreak Attacks and Defenses Against Large Language Models: A Survey](https://mlsanity.com/paper/2407.04295/) (2024)
- [OpenAGI: When LLM Meets Domain Experts](https://mlsanity.com/paper/2304.04370/) (2023)
- [Automatically Auditing Large Language Models via Discrete Optimization](https://mlsanity.com/paper/2303.04381/) (2023)
- [Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking](https://mlsanity.com/paper/2311.09827/) (2023)
- [Adversarial Attacks and Defenses in Large Language Models: Old and New Threats](https://mlsanity.com/paper/2310.19737/) (2023)

## Built on by (most cited first, 11 of 11)

- [Jailbreak Attack Initializations as Extractors of Compliance Directions](https://mlsanity.com/paper/2502.09755/) (2025)
- [Safety Alignment of LMs via Non-cooperative Games](https://mlsanity.com/paper/2512.20806/) (2025)
- [Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense](https://mlsanity.com/paper/2510.01088/) (2025)
- [MIST: Jailbreaking Black-box Large Language Models via Iterative Semantic Tuning](https://mlsanity.com/paper/2506.16792/) (2025)
- [SoK: Robustness in Large Language Models against Jailbreak Attacks](https://mlsanity.com/paper/2605.05058/) (2026)
- [Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking](https://mlsanity.com/paper/2605.29237/) (2026)
- [LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems](https://mlsanity.com/paper/2509.10682/) (2025)
- [PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents](https://mlsanity.com/paper/2605.10341/) (2026)
- [LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models](https://mlsanity.com/paper/2605.21362/) (2026)
- [The Safeguard Worked. Is the LLM System Safer?](https://mlsanity.com/paper/2609.00519/) (2026)
- [Toward Secure AI-Powered Penetration Testing Agents: Security Threats, Guardrails, and Architectural Perspectives](https://mlsanity.com/paper/2609.16694/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipulate prompts to induce harmful outputs. Exploring jailbreak attacks enables us to investigate the vulnerabilities of LLMs and further guides us in enhancing their security. Unfortunately, existing techniques mainly rely on handcrafted templates or generated-based optimization, posing challenges in scalability, efficiency and universality. To address these issues, we present JailPO, a novel black-box jailbreak framework to examine LLM alignment. For scalability and universality, JailPO meticulously trains attack models to automatically generate covert jailbreak prompts. Furthermore, we introduce a preference optimization-based attack method to enhance the jailbreak effectiveness, thereby improving efficiency. To analyze model vulnerabilities, we provide three flexible jailbreak patterns. Extensive experiments demonstrate that JailPO not only automates the attack process while maintaining effectiveness but also exhibits superior performance in efficiency, universality, and robustness against defenses compared to baselines. Additionally, our analysis of the three JailPO patterns reveals that attacks based on complex templates exhibit higher attack strength, whereas covert question transformations elicit riskier responses and are more likely to bypass defense mechanisms.