News for hackers. Stuff that matters.

A comment on LLM4Decompile: Decompiling Binary Code with LLM.

Re:LLM4Decompile: Decompiling Binary Code with LLM by kukas on Sunday March 17, 2024 @07:53AM (#39733806)
Hey, I am working on my own LLM-based decompiler for Python bytecode (https://github.com/kukas/deepcompyle). I feel there are not many people working on this research direction but I think it could be quite interesting, especially now that longer attention contexts are becoming feasible. If anyone knows a team that is working on this, I would be quite interested in cooperation.
[ Parent | on HN ]
Re:LLM4Decompile: Decompiling Binary Code with LLM by ok123456 on Sunday March 17, 2024 @12:55PM (#39735843)
Is there a benefit from using an LLM for Python byte code? Python byte code is high enough level that it's possible to translate it directly to source code from my experience.
[ Parent | on HN ]
Re:LLM4Decompile: Decompiling Binary Code with LLM by kukas on Sunday March 17, 2024 @01:36PM (#39736229)
My motivation is that the existing decompilers work only for Python versions till ~3.8. Having a model that could be finetuned with every new Python version release might overcome the need for highly specialized programmer that is able to update the decompiler to be compatible with the new version.

It is also a toy example for me to set up a working pipeline and then try to decompile more interesting targets.

[ Parent | on HN ]
Re:LLM4Decompile: Decompiling Binary Code with LLM by a2code on Sunday March 17, 2024 @05:56PM (#39738413)
Why Python? First, python is a language with a large open-source library. Second, I do not think it is used for software that is distributed as binaries?
[ Parent | on HN ]
Re:LLM4Decompile: Decompiling Binary Code with LLM by Retr0id on Sunday March 17, 2024 @09:39PM (#39739757)
Closed-source python exists, and it is frequently distributed in compiled binaries (especially in mediocre malware).

As a (supposedly) non-malicious example, the "Nightshade" watermarking tool is distributed as closed-source pre-compiled Python https://nightshade.cs.uchicago.edu/downloads.html

[ Parent | on HN ]
Re:LLM4Decompile: Decompiling Binary Code with LLM by maple3142 on Monday March 18, 2024 @05:05AM (#39741720)
There is [PyLingual](https://pylingual.io/), but it is not open source unfortunately. I am not sure if it is also LLM based.
[ Parent | on HN ]