Jailbreaking Large Language Models Through Content Concretization
This exposes critical vulnerabilities in LLM safety frameworks, posing risks for cybersecurity and content generation applications.
The paper tackles the vulnerability of LLM safety mechanisms by introducing Content Concretization, a jailbreaking technique that transforms abstract malicious requests into concrete implementations, achieving a success rate increase from 7% to 62% on cybersecurity prompts at a cost of 7.5¢ per prompt.
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 \textit{Content 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 7.5\textcent~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.