Programming

29051 readers

306 users here now

Welcome to the main community in programming.dev! Feel free to post anything relating to programming here!

Cross posting is strongly encouraged in the instance. If you feel your post or another person's post makes sense in another community cross post into it.

Hope you enjoy the instance!

Rules

Follow the programming.dev instance rules
Keep content related to programming in some way
If you're posting long videos try to add in some form of tldr for those who don't want to watch videos

Wormhole

Follow the wormhole through a path of communities !webdev@programming.dev

founded 3 years ago

MODERATORS

snowe@programming.dev

Ategon@programming.dev

UlrikHD@programming.dev

bugsmith@programming.dev

Spyro@programming.dev

What's the state of LLM powered decompilation right now, or do you think it will ever work? (lemmy.world)

submitted 1 day ago by yogurtwrong@lemmy.world to c/programming@programming.dev

21 comments fedilink hide all child comments

I am aware of existing decompilation tools like Ghidra which give you close-to-original pseudocode.

But I think reverse engineering might be a place for ML to shine... After all, you got an empty source file, and a target binary to reach. You can automatically check everything by doing test compilations and comparing with the target binary.

ML is really good for pattern recognition, which is a huge part of reverse engineering. Though at the same time, I experienced firsthand how bad LLMs are in assembly since they don't "think" or have a hard time tracking state machines.

I am aware that a big part of reverse engineering is not getting something that compiles, but rather, figuring out variable names, function definitions and how a piece of software works in general. But I think, with human help, it could help decompilations drastically. What do you think?

you are viewing a single comment's thread
view the rest of the comments

[–] Kissaki@programming.dev 3 points 1 day ago

The advantage of decompilation as a task is that you have a reference output you can validate against.

I would assume the approach, mechanisms, and quality of produced code is similar to general/prompted code generating.

I assume the produced code (and its quality) depends on the compiled code; how much was stripped or obfuscated, and what runtime are we talking about which may or may not have language constructs that guide structure. With little metadata or code structure left AI would shift more into it's general patterns than if there is more metadata available that already defines structures or names.

The thought of integrating a deterministic decompiler and then use AI to structure it and make it more readable while verifying the output remains the same seems like an interesting extension or alternative workflow and toolchain.

I have not used these kinds of AI decompilation tools or workflows, but thinking purely from my background and general experience.