# Jailbreaking Large Language Models Through Content Concretization

arXiv: https://arxiv.org/abs/2509.12937 · HTML: https://mlsanity.com/paper/2509.12937/

## 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 12 of its 19 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Placed in

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

## Builds on (most cited first, 12 of 12)

- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs](https://mlsanity.com/paper/2402.11753/) (2024)
- [COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability](https://mlsanity.com/paper/2402.08679/) (2024)
- [Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues](https://mlsanity.com/paper/2402.09091/) (2024)
- [When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers](https://mlsanity.com/paper/2402.10601/) (2024)
- [WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response](https://mlsanity.com/paper/2405.14023/) (2024)
- [The Jailbreak Tax: How Useful are Your Jailbreak Outputs?](https://mlsanity.com/paper/2504.10694/) (2025)
- [SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains](https://mlsanity.com/paper/2411.06426/) (2024)
- [Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions](https://mlsanity.com/paper/2502.04322/) (2025)
- [CySecBench: Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models](https://mlsanity.com/paper/2501.01335/) (2025)
- [Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion](https://mlsanity.com/paper/2505.14316/) (2025)
- [Prompt, Divide, and Conquer: Bypassing Large Language Model Safety Filters via Segmented and Distributed Prompt Processing](https://mlsanity.com/paper/2503.21598/) (2025)

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

- [Intent Laundering: AI Safety Datasets Are Not What They Seem](https://mlsanity.com/paper/2602.16729/) (2026)
- [Beyond Context: Large Language Models' Failure to Grasp Users' Intent](https://mlsanity.com/paper/2512.21110/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly deployed for task automation and content generation, yet their safety mechanisms remain vulnerable to circumvention through different jailbreaking techniques. In this paper, we introduce textitContent Concretization (CC), a novel jailbreaking technique that iteratively transforms abstract malicious requests into concrete, executable implementations. CC is a two-stage process: first, generating initial LLM responses using lower-tier, less constrained safety filters models, then refining them through higher-tier models that process both the preliminary output and original prompt. We evaluate our technique using 350 cybersecurity-specific prompts, demonstrating substantial improvements in jailbreak Success Rates (SRs), increasing from 7% (no refinements) to 62% after three refinement iterations, while maintaining a cost of 7.5textcent~per prompt. Comparative A/B testing across nine different LLM evaluators confirms that outputs from additional refinement steps are consistently rated as more malicious and technically superior. Moreover, manual code analysis reveals that generated outputs execute with minimal modification, although optimal deployment typically requires target-specific fine-tuning. With eventual improved harmful code generation, these results highlight critical vulnerabilities in current LLM safety frameworks.