this post was submitted on 30 Oct 2026
28 points (88.9% liked)

Programming

29080 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

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
 

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?

top 24 comments
sorted by: hot top controversial new old
[–] 4am@lemmy.zip 23 points 2 days ago (2 children)

I think it’ll be used to push everything I to the cloud since they can “no longer trust putting code on user’s local machines” and we will all have to rent streamed software experienced for the rest of our lives or be unable to function in society.

Honestly fuck capitalism for taking us down this road.

[–] fonix232@fedia.io 3 points 2 days ago

That won't be a sustainable option for most software, as they need to work offline, plus a majority of customers still live in areas where reliable high bandwidth internet (a requirement for streaming software at any usable rate) isn't really available.

[–] entwine@programming.dev -5 points 2 days ago (2 children)

Honestly fuck capitalism for taking us down this road.

Capitalism has nothing to do with this. It's corruption, incompetent politicians, and a lazy populace who would rather bitch online than go out and vote (something I'm definitely guilty of, but am actively working to change)

The direction things are going are to concentrate wealth and power into the hands of a very small group of assholes. There is no economic or political system that can fix the problems those assholes have been exploiting to pull this off. The only thing that can prevent that is an informed and energized population of voters.

Like, we all want to see Trump, Musk, Zuckerberg, etc in prison. It feels like they're untouchable, but literally all it would take to do that is to spend a few minutes filling out a ballot to get rid of the career politicians who have been in office too long (and thus are more likely to be corrupt). Even local elections matter.

[–] PoY@lemmygrad.ml 4 points 1 day ago (1 children)

"it's not the very system we live and work under that are responsible for the ill effects in all facets of our lives, it's just some random luck that a few people get to make all the decisions that benefit them at the expense of everyone and everything else!"

you sound silly

[–] entwine@programming.dev 0 points 1 day ago

Of course I sound silly. You're putting your words in my mouth.

[–] Senal@programming.dev 14 points 2 days ago* (last edited 2 days ago)

so.....the extended consequences of rampant capitalism ?

well...rampant "people gonna people" but capitalism is the current favoured expression of that.

[–] JohnnyCanuck@lemmy.ca 26 points 2 days ago (2 children)

Yeah, this is all over tech news for the past month. The entire Adobe creative suite got reverse engineered. Someone reverse engineered Skate and combined it with Call of Duty or something.

The big companies are suddenly talking about how bad AI is...

https://github.com/songshikang0111/awesome-REA-cases

[–] hendrik@palaver.p3x.de 53 points 2 days ago* (last edited 2 days ago) (1 children)

To be fair, technically, the Adobe suite didn't get reverse engineered, instead they vibe-coded a clone.

[–] kernelpanic@piefed.blahaj.zone 3 points 2 days ago (1 children)

I'm interested in more context and sources about this

[–] mesamunefire@piefed.social 4 points 2 days ago

Windows 11 is getting reverse engineered. Hilarious.

[–] melfie@lemmy.zip 8 points 2 days ago* (last edited 2 days ago) (1 children)

I tested REA with Qwen 3.8 27B with a narrow solver capability from some commercial 3d software and it was quick to extract 20,000 lines of Ghidra C-like pseudocode, but painfully slow to turn it into actual C++. It struggled interpreting all the matrix math and making something that actually worked. I stopped after a couple days of it churning, figuring it could spend a couple weeks and end up with worthless slop. I’m a software engineer and don’t have a background in RE, so maybe someone with more experience would do better.

[–] LouNeko@lemmy.world 2 points 2 hours ago (1 children)

Qwen 3.8 is not the smartest cookie when it comes to math. If the math is based on a research paper you can usually chug it in the context and it actually manages to one-shot the solution. But just from code alone it's not smart enough to figure out what the purposes of some matrices are and formulae are. I'd say it's on a junior coder level, it needs to get access to further research to actually understand implementations.

[–] melfie@lemmy.zip 1 points 1 hour ago

It would seem so and I’m guessing it might do better with REA and something that isn’t math-heavy. What surprised me most is that it dove right in even though it’s supposed to refuse RE.

De-obfuscation is probably one of the few ok uses for a ethically trained LLM

[–] Damarus@feddit.org 6 points 2 days ago

It works and I've been playing around with it for the past week. Not really knowing what I'm doing, because my background is in software development, not reverse engineering, I've been running into the usual problems with badly guided agents. My project is cluttered, I don't really know what's important, progress is rather slow. But there is progress and I'm sure someone with more RE knowledge can make the process more efficient.

I'm looking forward to getting some of my favourite old games running on modern systems using this.

[–] Kissaki@programming.dev 3 points 2 days 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.

[–] LouNeko@lemmy.world 4 points 2 days ago (1 children)

Given what is happening to Project Zombiod right now... I think it working pretty darn well.

[–] LowtierComputer@lemmy.world 8 points 2 days ago (1 children)
[–] LouNeko@lemmy.world 0 points 2 days ago (1 children)
[–] LowtierComputer@lemmy.world 7 points 2 days ago (2 children)

What's happening with project zomboid and AI?

[–] LouNeko@lemmy.world 1 points 1 hour ago

So Project Zomboid is a 2.5D (2D sprites, 3D characters) Isometric game. For years people fantasized about it being in the first person perspective. The devs clearly stated that this is impossible on a fundamental engine level. Over the past 2 months people used AI to completely dissect the source code of the game and do the impossible. They created a mod called Project Viewpoint that turned all the 2D assets into 3D models and allowed to play in third and first person perspective.

This is an incredible feat. Imagine somebody would make a mod to freely rotate the camera in Age of Empires 2, a fully sprite driven 2D isometric game.

Further than that, people started to decomplie a lot of other games and scrap them for mechanics and assets. Project Viewpoint has become the driving force for advanced modding. They added the animations and weapons from Escape from Tarkov, the parkour mechanics from Mirrors Edge, the vehicle physics from BeamNG and so on and so on.

Project Zomboid is on it's way to truly become an everything game driven by AI assisted modding.

Even if it seems like the devs are losing control over their own game, for now they did the right thing. They acknowledged the current situation and warned people to be carefull with Javascript based mods that can execute malicious code, while not condoning the development of the modding scene and AI use.

Here's the devs community post:
https://store.steampowered.com/news/app/108600/view/672883630592229814?l=english

[–] Quetzalcutlass@lemmy.world 8 points 2 days ago

Someone vibe-coded a mod that turns the whole game first person.

[–] thingsiplay@lemmy.ml 2 points 2 days ago

I think for the long term success, they need to write better readable code. But this only comes after the legal part is solved, in example how copyright is handled if an Ai is involved.