大型语言模型是少样本生成器:提出混合提示算法生成Webshell逃逸样本
Large Language Models are Few-shot Generators: Proposing Hybrid Prompt Algorithm To Generate Webshell Escape Samples
AI总结:
本文提出Hybrid Prompt算法,利用大型语言模型结合多种提示思想与Webshell分层模块生成高质量逃逸样本,显著提升了逃逸率和存活率,推动了AI-based Webshell检测研究。
摘要:
网络攻击的频繁发生使得Webshell攻击与防御逐渐成为网络安全领域的研究热点。然而,公开可用的基准数据集缺乏,以及Webshell逃逸样本生成过度依赖人工定义的规则,减缓了Webshell逃逸样本生成和基于人工智能(AI)的Webshell检测相关研究的进展。为了解决Webshell样本逃逸能力弱、缺乏具有复杂恶意特征的Webshell数据集等不足,并促进Webshell检测的发展,我们借助大型语言模型提出了用于Webshell逃逸样本生成的Hybrid Prompt算法。作为专门为Webshell样本生成而开发的提示算法,Hybrid Prompt算法不仅结合了包括Chain of Thought、Tree of Thought在内的多种提示思想,还融合了Webshell分层模块和few-shot示例等多种组件,以帮助LLM学习和推理Webshell逃逸策略。实验结果表明,Hybrid Prompt算法可以与多个具有出色代码推理能力的LLM协同工作,生成高质量的Webshell样本,具有高逃逸率(使用GPT-4模型在VirusTotal检测引擎上为88.61%)和存活率(使用GPT-4模型为54.98%)。
英文摘要:
The frequent occurrence of cyber-attacks has made webshell attacks and defense gradually become a research hotspot in the field of network security. However, the lack of publicly available benchmark datasets and the over-reliance on manually defined rules for webshell escape sample generation have slowed down the progress of research related to webshell escape sample generation and artificial intelligence (AI)-based webshell detection. To address the drawbacks of weak webshell sample escape capabilities, the lack of webshell datasets with complex malicious features, and to promote the development of webshell detection, we propose the Hybrid Prompt algorithm for webshell escape sample generation with the help of large language models. As a prompt algorithm specifically developed for webshell sample generation, the Hybrid Prompt algorithm not only combines various prompt ideas including Chain of Thought, Tree of Thought, but also incorporates various components such as webshell hierarchical module and few-shot example to facilitate the LLM in learning and reasoning webshell escape strategies. Experimental results show that the Hybrid Prompt algorithm can work with multiple LLMs with excellent code reasoning ability to generate high-quality webshell samples with high Escape Rate (88.61% with GPT-4 model on VirusTotal detection engine) and (Survival Rate 54.98% with GPT-4 model).
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。