{"id":5276,"date":"2025-04-15T06:22:09","date_gmt":"2025-04-15T04:22:09","guid":{"rendered":"https:\/\/security.humanativaspa.it\/?p=5276"},"modified":"2025-10-21T09:04:37","modified_gmt":"2025-10-21T09:04:37","slug":"aiding-reverse-engineering-with-rust-and-a-local-llm","status":"publish","type":"post","link":"https:\/\/hnsecurity.it\/it\/blog\/aiding-reverse-engineering-with-rust-and-a-local-llm\/","title":{"rendered":"Aiding reverse engineering with Rust and a local LLM"},"content":{"rendered":"

“A large fraction of the flaws in software development are due to programmers not fully understanding all the possible states their code may execute in.”
\n— John Carmack<\/em><\/p>\n

“Can it run Doom?”
\n— canitrundoom.org<\/a><\/em><\/p><\/blockquote>\n

TL;DR<\/h3>\n

There\u2019s a new entry in my ever-growing vulnerability divination<\/em> tool suite<\/a>, designed to assist with reverse engineering and <\/strong>vulnerability research against binary targets<\/strong>: oneiromancer.<\/a><\/p>\n

It’s a reverse engineering assistant that uses a fine-tuned<\/a>, locally running LLM to aid with code analysis<\/strong>. It can analyze a function or a smaller code snippet, returning a high-level description of what the code does, a recommended name for the function, and variable renaming suggestions based on the results of the analysis.<\/p>\n

As you’ve probably guessed, oneiromancer is written in Rust<\/strong> \ud83e\udd80 While working on this tool, I also contributed<\/a> the new security<\/em> category<\/a> to crates.io. I hope you’ll find it useful for your projects.<\/p>\n

\n

My first official rust-lang contribution \ud83d\ude1chttps:\/\/t.co\/SLQ0tnSGXj<\/a><\/p>\n

On https:\/\/t.co\/Uo0aEhEXyU<\/a>, you can now categorize your crates under \u201csecurity\u201d (\u201cCrates related to cybersecurity, penetration testing, code review, vulnerability research, and reverse engineering.\u201d).<\/p>\n

— raptor@infosec.exchange (@0xdea) March 28, 2025<\/a><\/p><\/blockquote>\n