undefined | Better HN

0 pointsctoth11mo ago0 comments

Have you seen this?

What they do is ground the LLM to the AST with Babel to ensure you still get the same shape of AST out of your deobfuscation pass. Probably this tool could be cleaned up, made to work with multiple llm and parser backends, have its prompts improved, &c.

0 comments

rfoo11mo ago

This is great idea! But it's more about having LLMs to give function & variables names, instead of having LLM to deobfuscate. The (traditional) deobfuscations (e.g. unpack, de-flatten, de-virtualization etc) were done by 100% precise human made Babel plugins and is totally unrelated to a LLM.

j / k navigate · click thread line to collapse

0 pointsctoth11mo ago0 comments

Have you seen this?

https://github.com/jehna/humanify

0 comments

rfoo11mo ago

j / k navigate · click thread line to collapse