G-3PO: A Protocol Droid for Ghidra, or GPT-3 for Reverse-Engineering

• ghidra_tools

  6 281 5.4 Python

  A collection of Ghidra scripts, including the GPT-3 powered code analyser and annotator, G-3PO.

  

A few days ago this went mostly ignored (https://news.ycombinator.com/item?id=34161642) and I was asked to re-submit it (https://news.ycombinator.com/item?id=34250150) so that it gets a second chance.

That’s a script for the reverse-engineering tool Ghidra that uses GPT-3 to de-compile machine code and to write plain English explanations of what a piece of code does.

The article is quite detailed and describes both its capabilities and its limitations. That G-3PO script is open source, MIT license: https://github.com/tenable/ghidra_tools/tree/main/g3po

There was also another HN story about what at first sight looks like an alternative implementation of the same idea: “GptHidra – Ghidra plugin that asks OpenAI Chat GPT to explain functions”

https://news.ycombinator.com/item?id=34165291

This one is more recent and lacks that good write-up mentioned above. The script is smaller and it seems to have fewer features.

I suggest checking both of them.

• Gepetto

  12 2,667 4.5 Python

  IDA plugin which queries OpenAI's GPT language models to speed up reverse-engineering

I'm partial to Gepetto for IDA, which includes an especially hilarious trick in which it instructs ChatGPT to phrase its responses in JSON, and then uses this JSON directly to name variables in the decompilation. If the JSON is incorrect, it politely asks ChatGPT to please fix its JSON output, which usually works.

https://github.com/JusticeRage/Gepetto/blob/main/gepetto.py#...

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• gpt-wpre

  3 337 10.0 Python

  Whole-Program Reverse Engineering with GPT-3

Very neat! I also worked on something that uses GPT-3 for reverse engineering last week. The basic idea is that right now GPT-3 is limited in how much context it can see at once. So instead, to summarize a function in context, I use the call graph to find all of its dependencies, and summarize them one by one, providing the summaries of the callees when summarizing the caller:

https://github.com/moyix/gpt-wpre

• Ghidra-ChatGPT

  3 88 0.0 Python

That's awesome! I also wanted to combine Ghidra and GPT3, but I was unsure about its capabilities to explain code. I made a plugin where you highlight part of the listing view and it explains what is going on with the help of ChatGPT. Link for the curious: https://github.com/SourceDiver42/Ghidra-ChatGPT

Suggest a related project