MGC：一种利用对齐大语言模型组合盲区生成恶意软件的编译器框架
MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation
AI总结：
本文提出恶意软件生成编译器MGC，通过模块化分解恶意任务并利用MDIR生成看似无害的代码片段，以规避对齐LLM的防护，实验表明其生成正确性显著优于越狱方法和地下服务。
摘要：
大语言模型（LLMs）已使软件开发大众化，降低了编程复杂应用的专业门槛。这种易用性也延伸至恶意软件开发，引发了重大安全担忧。尽管LLM提供商已实施对齐机制以防止直接生成明显恶意的代码，但这些防护措施主要孤立地评估单个提示，忽视了一个关键漏洞：恶意操作可被系统性地分解为看似无害的子任务。本文提出了恶意软件生成编译器（MGC），一个通过模块化分解和对齐规避生成来利用该漏洞的新型框架。MGC采用专门的恶意软件描述中间表示（MDIR）来桥接高层恶意意图与看似无害的代码片段。广泛评估表明，我们的攻击能够在多样的任务规格和类别中可靠地生成功能性恶意软件，在三个基准数据集上的正确性方面比越狱方法高出+365.79%，比地下服务高出+78.07%。案例研究进一步显示，MGC能够复现甚至增强16个真实世界恶意软件样本。这项工作通过揭示针对对齐AI系统的组合攻击风险，为安全研究人员提供了关键见解。演示可在https://sites.google.com/view/malware-generation-compiler获取。
英文摘要：
Large language models (LLMs) have democratized software development, reducing the expertise barrier for programming complex applications. This accessibility extends to malicious software development, raising significant security concerns. While LLM providers have implemented alignment mechanisms to prevent direct generation of overtly malicious code, these safeguards predominantly evaluate individual prompts in isolation, overlooking a critical vulnerability: malicious operations can be systematically decomposed into benign-appearing sub-tasks. In this paper, we introduce the Malware Generation Compiler (MGC), a novel framework that leverages this vulnerability through modular decomposition and alignment-evasive generation. MGC employs a specialized Malware Description Intermediate Representation (MDIR) to bridge high-level malicious intents and benign-appearing code snippets. Extensive evaluation demonstrates that our attack reliably generates functional malware across diverse task specifications and categories, outperforming jailbreaking methods by +365.79% and underground services by +78.07% in correctness on three benchmark datasets. Case studies further show that MGC can reproduce and even enhance 16 real-world malware samples. This work provides critical insights for security researchers by exposing the risks of compositional attacks against aligned AI systems. Demonstrations are available at https://sites.google.com/view/malware-generation-compiler.
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。
