EquaCode: A Multi-Strategy Jailbreak Approach for Large Language Models via Equation Solving and Code Completion

TL;DR

EquaCode introduces a multi-strategy jailbreak method combining equation solving and code completion to effectively bypass large language model safety measures, revealing vulnerabilities across multiple models with high success rates.

Contribution

The paper presents a novel multi-strategy jailbreak approach that outperforms single-strategy methods, significantly improving the effectiveness of testing LLM robustness against safety constraints.

Findings

Achieves over 91% success rate on GPT series models

Reaches 98.65% success across three state-of-the-art LLMs

Demonstrates the synergistic effect of combining equation solving and code completion

Abstract

Large language models (LLMs), such as ChatGPT, have achieved remarkable success across a wide range of fields. However, their trustworthiness remains a significant concern, as they are still susceptible to jailbreak attacks aimed at eliciting inappropriate or harmful responses. However, existing jailbreak attacks mainly operate at the natural language level and rely on a single attack strategy, limiting their effectiveness in comprehensively assessing LLM robustness. In this paper, we propose Equacode, a novel multi-strategy jailbreak approach for large language models via equation-solving and code completion. This approach transforms malicious intent into a mathematical problem and then requires the LLM to solve it using code, leveraging the complexity of cross-domain tasks to divert the model's focus toward task completion rather than safety constraints. Experimental results show that Equacode achieves an average success rate of 91.19% on the GPT series and 98.65% across 3 state-of-the-art LLMs, all with only a single query. Further, ablation experiments demonstrate that EquaCode outperforms either the mathematical equation module or the code module alone. This suggests a strong synergistic effect, thereby demonstrating that multi-strategy approach yields results greater than the sum of its parts.