Show HN:Revenant – 全自动 LLM 驱动的逆向工程和重实现
3 分•作者: sylwester•4 个月前
我是一名硬件工程师和安全研究员,一直在思考我的工作是否可以部分自动化,以便我能专注于其他领域。因此,我构建了 Revenant——一个由大型语言模型(Claude、OpenAI、本地 AI)驱动的工具包,它围绕 radare2、ghidra 等工具构建,能够完全自动分析固件,实现开源骨架,包括引脚定义、硬件启动、外设启动等,甚至可以一对一复制现有固件,从而让旧硬件能够使用现代工具链复活。
一些应用包括:
* 让旧硬件焕发新生
* 对可疑固件进行安全分析
请在以下地址查看:
<a href="https://github.com/DatanoiseTV/revenant" rel="nofollow">https://github.com/DatanoiseTV/revenant</a>
我非常希望收到关于此项目的反馈和改进建议。
查看原文
I am a hardware engineer and security researcher and I've been wondering whether my work could be partially automated, so I can focus on other topics as well, so I build revenant - a LLM powered (Claude, OpenAI, local AI) toolkit that builds around radare2, ghidra etc and can fully automatically analyze firmware, implement open source skeletons incl. pinouts, hardware bringup, peripheral bringup etc. or can even 1:1 replicate existing firmware so old hardware can be resurrected with modern toolchains.<p>Some applications are:<p>- Give old hardware new life<p>- Security Analysis of shady firmware<p>Check it at:
<a href="https://github.com/DatanoiseTV/revenant" rel="nofollow">https://github.com/DatanoiseTV/revenant</a><p>I would love some input on this and maybe some recommendations for improvements.