Exeter, UK · Founder, Arbiter Security

Laurence Avent

Security engineer building AI-native offensive tooling in Rust, with a sideline in reasoning a machine can re-check. I work where security engineering, language models, and formal verification meet.


Work

What I build

Venture

Arbiter Security

AI-native offensive security tools, built in Rust. Two products exposed as MCP servers: Arbiter (web-application vulnerability detection across 52 classes) and Aletheia (binary analysis across 14 CWE classes).

Civic data

Tightrope Tracker

An open-source live dashboard of UK economic constraint, drawn from official OBR and ONS sources, with public methodology and codebase.

Open source

Security & AI tooling

Narsil-MCP (a 90-tool code-intelligence server), Forgemax (a V8 sandbox for LLM execution), Veilguard, Sanctum, and Krait.


Research

Reasoning that carries its own proof

A working system in which untrusted generators, language models among them, propose reasoning steps, a small kernel enforces the rules, and every accepted chain is re-checked byte-for-byte and re-proved in Lean 4. Its first case study is a determination of the van der Waerden number W(3,3); the papers and artifacts are on the research page.

Framework

Avent's Razor

Judge a reasoning system by the constraints it can enforce during search: enforcement prunes the space and, unlike insight, can be checked by machine.

Systems

Verified Chain-of-Thought

An 18-rule kernel, two independent byte-level checkers held to exact agreement, and a Lean 4 oracle that re-proves every step. Language models operate the loop through a typed gate.

Case study

W(3,3) = 27

Both directions machine-checked: a 382,964-step certificate covering the entire search, compiled to Lean and reduced to a single biconditional over colourings.


Contact

Get in touch

Open to conversations about security engineering, coordinated disclosure, and verified reasoning. Email is the fastest route.