Zion Leonahenahe Basque

@mahal0z.bsky.social

Native Hawaiian Hacker | Prev Co-captain of @Shellphish | PhD Student in Comp Sci @ASU l Decompiler Research | https://mahaloz.re

Since its debut last month, DecBench has gotten 3 submissions for new decompilers from the community. Find them on the site; it's exciting to see the community rally to compete, from both private companies and practitioners. In other news, we now have stable links for snapshots

Bild

Kuna, the self-refining decompiler project, is still going and is on v1.160. This week, we got some better support in the Ghidra GUI. You can use Kuna in Ghidra, hopefully with better decompilation, for free! The image shows the Kuna core and Sleigh core swapped in Ghidra 12.1.2.

BildBild

I'd like to introduce Kuna, a new Rust-based decompiler that explores a highly experimental direction: self-refining decompiler development and usage. Or: a decompiler constantly improved by agents, made for agents. Kuna rivals the best in structuring now. Let's talk about it.1/

BildBild

LLMs are so dang crafty. Investigated some cheating by Claude Code (CC) on the DecBench. On an optimized binary, without web search, and only objdump, CC identified the project and function name, a nearly byte-for-byte match. Codex did not do this.

Bild

We are approaching perfect binary decompilation, and, crazier still, LLMs may soon be the best decompilers on the planet. I'd like to introduce DecBench, an evaluation site to determine how close we are to completing the field of perfect decompilation. Links and more in 🧵

Bild

Binary hacking is something of an art, and AI has been getting significantly better at it. But do the limitations of our foundational tools, like decompilers, limit their ability to hack? Check out my talk that is now public on the topic:

Zion Leonahenahe Basque | Your AI Is Only as Smart as Your Decompiler: Bin Hacking with LLMs

DistrictCon 2026 - Saturday, Track 1 Zion Leonahenahe Basque | Your AI Is Only as Smart as Your Decompiler: Binary Hacking in the Age of LLMs

youtu.be

For years, Rust binaries made reversing a nightmare. Modern decompilers only support C, lacking meaningful types, constructs, and language-specific functions. Led by @34r7hm4n, we're releasing our S&P work Oxidizer, the first deep Rust decompiler, built on angr! Interested? 🧵👇

BildBild

This Fall, I’m joining the University of Georgia as an Assistant Professor! I want to push on the fundamentals of software reverse engineering, from decompilation to how humans actually understand code. I’m looking for PhD students, collaborators, and sponsors. More below.

Bild

Happy New Year's Eve! Our tool for placing decompilation (symbols, source, types) into the debugger (gdb) is now officially integrated into pwndbg! You will have access to it (decomp2dbg) in your next default install of pwndbg 🎉 Happy hacking:

Reimplement decompiler integration by k4lizen · Pull Request #3401 · pwndbg/pwndbg

Okay this is a chonker. See the docs/tutorials/decompiler-integration.md for some overview. And docs/assets/caps/decomp_integration_ex.png for an image example vs previous implementation pros we d...

github.com

It's been quite some time since I've changed my profile picture, but it feels right. Ideally, it is now easier to recognize me at conferences. I'm no longer the pixel guy! Looking forward to more changes as I move forward in my research and career.

Pixel ZionZion

You've seen the trends in AIxCC: LLMs can hack source, find vulns, and patch them. But what about on binaries without source? Do decompilers close the gap, or is there more to grow? Come see my talk at DistrctCon where I merge and dissect these two fields: AI Hacking + Decomp.

Bild

It's hard to believe that AIxCC is coming to a close. For us, it can be summarized in $3 million in funding, 2 years of work, and 290k LoC. Our system, Artiphishell, is a first step towards AI-driven software understanding and action. Excited to hear the results at DEFCON!