arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2308.09183cs.CRcs.LG
收藏

RatGPT:将在线 LLMs 转变为恶意软件攻击的代理

RatGPT: Turning online LLMs into Proxies for Malware Attacks

Luxembourg Tech School asbl(卢森堡技术学校协会)

Mika Beckerich, Laura Plein, Sergio Coronado

AI总结:

本研究利用公开插件将在线 LLM(如 ChatGPT)作为攻击者与受害者间的代理,提出 RatGPT 概念验证,实现恶意软件传播、规避检测及 C2 服务器通信,揭示了 LLM 插件的网络安全风险并呼吁制定缓解策略。

摘要:

生成式 AI 的演进以及最新发布的大型语言模型(LLMs)的能力为软件工程带来了新机遇。然而,它们也给网络安全带来了新挑战。最近,研究人员展示了使用诸如 ChatGPT 等 LLMs 生成恶意内容的可能性,这些内容可直接被利用或指导缺乏经验的黑客将工具和代码武器化。这些研究涵盖的场景仍需攻击者处于中间环节。在本研究中,我们利用公开可用的插件,并使用 LLM 作为攻击者与受害者之间的代理。我们提供了一个概念验证,其中使用 ChatGPT 进行恶意软件的传播并规避检测,同时建立与命令与控制(C2)服务器的通信,以接收命令并与受害者的系统进行交互。最后,我们介绍了保持不被检测并使攻击成功的一般方法及关键要素。该概念验证突显了公开可用的插件和 LLMs 带来的重大网络安全问题,需要制定安全指南、控制措施和缓解策略。

英文摘要:

The evolution of Generative AI and the capabilities of the newly released Large Language Models (LLMs) open new opportunities in software engineering. However, they also lead to new challenges in cybersecurity. Recently, researchers have shown the possibilities of using LLMs such as ChatGPT to generate malicious content that can directly be exploited or guide inexperienced hackers to weaponize tools and code. These studies covered scenarios that still require the attacker to be in the middle of the loop. In this study, we leverage openly available plugins and use an LLM as proxy between the attacker and the victim. We deliver a proof-of-concept where ChatGPT is used for the dissemination of malicious software while evading detection, alongside establishing the communication to a command and control (C2) server to receive commands to interact with a victim's system. Finally, we present the general approach as well as essential elements in order to stay undetected and make the attack a success. This proof-of-concept highlights significant cybersecurity issues with openly available plugins and LLMs, which require the development of security guidelines, controls, and mitigation strategies.

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。

↑