Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them

quesma.com

Post reply on HN
Print view View original

51–60 of 108 posts

Re: We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them

#51

Post by eli »

akiselev wrote: post #40
7777332215 wrote: post #26

I know they said they didn't obfuscate anything, but if you hide imports/symbols and obfuscate strings, which is the bare minimum for any competent attacker, the success rate will immediately drop to zero. This is detecting the pattern of an anomaly in language associated with malicious activity, which is not impressive for an LLM.

When I was developing my ghidra-cli tool for LLMs to use, I was using crackmes as tests and it had no problem getting through obfuscation as long as it was prompted about it. In practice when reverse engineering real software it can sometimes spin in circles for a while until it finally notices that it's dealing with obfuscated code, but as long as you update your CLAUDE.md/whatever with its findings, it generally mo…

Is it also possible that crackme solutions were already in the training data?

Re: We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them

#53

Post by akiselev »

eli wrote: post #51
akiselev wrote: post #40

Earlier quoted context omitted.

When I was developing my ghidra-cli tool for LLMs to use, I was using crackmes as tests and it had no problem getting through obfuscation as long as it was prompted about it. In practice when reverse engineering real software it can sometimes spin in circles for a while until it finally notices that it's dealing with obfuscated code, but as long as you update your CLAUDE.md/whatever with its findings, it generally mo…

Is it also possible that crackme solutions were already in the training data?

I used the latest submissions from sites like crackmes.ones which were days or weeks old to guard against that.

Re: We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them

#55

Post by snovv_crash »

Roark66 wrote: post #31

And this one demonstration why these "1000 CTOs claim no effectiveness improvement after introducing AI in their companies" are 100% BS. They may have not noticed an improvement, but it doesn't mean there isn't any.

Even without AI, many (most?) orgs are held back by internal processes and politics, not development speed.

Re: We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them

#56

Post by shevy-java »

So the best one found about 50%. I think that is not bad, probably better than most humans. But what about the remaining 50%? Why were some found and others not?

> Claude Opus 4.6 found it… and persuaded itself there is nothing to worry about > Even the best model in our benchmark got fooled by this task.

That is quite strange. Because it seems almost as if a human is required to make the AI tools understand this.

Re: We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them

#57

Post by stared »

7777332215 wrote: post #26

I know they said they didn't obfuscate anything, but if you hide imports/symbols and obfuscate strings, which is the bare minimum for any competent attacker, the success rate will immediately drop to zero. This is detecting the pattern of an anomaly in language associated with malicious activity, which is not impressive for an LLM.

One of the authors here.

The tasks here are entry level. So we are impressed that some AI models are able to detect some patterns, while looking just at binary code. We didn't take it for granted.

For example, only a few models understand Ghidra and Radare2 tooling (Opus 4.5 and 4.6, Gemini 3 Pro, GLM 5) https://quesma.com/benchmarks/binaryaudit/#models-tooling

We consider it a starting point for AI agents being able to work with binaries. Other people discovered the same - vide https://x.com/ccccjjjjeeee/status/2021160492039811300 and https://news.ycombinator.com/item?id=46846101.

There is a long way ahead from "OMG, AI can do that!" to an end-to-end solution.

Re: We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them

#58

Post by openasocket »

Ummm, is it a good idea to use AI for malware analysis? I know this is just a proof of concept, but if you have actual malware, it doesn’t seem safe to hand that to AI. Given the lengths of anti-debugging that goes in existing malware, making something to prompt inject, or trick AI to execute something, seems easier.

Re: We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them

#59

Post by achille »

7777332215 wrote: post #26

I know they said they didn't obfuscate anything, but if you hide imports/symbols and obfuscate strings, which is the bare minimum for any competent attacker, the success rate will immediately drop to zero. This is detecting the pattern of an anomaly in language associated with malicious activity, which is not impressive for an LLM.

in the article they explicitly said they stripped symbols. If you look at the actual backdoors many are already minimal and quite obfuscated,

see:

- https://github.com/QuesmaOrg/BinaryAudit/blob/main/tasks/dns...

- https://github.com/QuesmaOrg/BinaryAudit/blob/main/tasks/dro...

Re: We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them

#60

Post by Retr0id »

7777332215 wrote: post #26

I know they said they didn't obfuscate anything, but if you hide imports/symbols and obfuscate strings, which is the bare minimum for any competent attacker, the success rate will immediately drop to zero. This is detecting the pattern of an anomaly in language associated with malicious activity, which is not impressive for an LLM.

Stripping symbols is fairly normal, but hiding imports ought to be suspicious in its own right.
Post reply on HN