AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models

In our research, we pioneer a novel approach to evaluate the effectiveness of jailbreak attacks on Large Language Models (LLMs), such as GPT-4 and LLaMa2, diverging from traditional robustness-focused binary evaluations. Our study introduces two distinct evaluation frameworks: a coarse-grained evaluation and a fine-grained evaluation. Each framework, using a scoring range from 0 to 1, offers a unique perspective, enabling a more comprehensive and nuanced evaluation of attack effectiveness and empowering attackers to refine their attack prompts with greater understanding. …

attacks binary cs.cl evaluation fine-grained framework frameworks gpt gpt-4 jailbreak language language models large language large language models llama2 llms novel research robustness study