Arkheia · Technical Rationale
Why Surface
Detection Works
Instead of asking "can we detect hallucinations?", ask: "can we measure and model surface behaviour?" That's a much more defensible — and answerable — question.
§ 01 · The Core Distinction
Not what's inside.
What comes out.
Output-only evaluation asks: "Is this response good?"
Surface-based detection asks: "Is this response consistent with how this model normally behaves?"
Behavioural deviation is detectable even when content appears normal. It's also detectable without reading the content at all — which is what makes it privacy-preserving by design, not by accident.
The defensible statement
"We measure and model surface behaviour — the statistics of invocation, signal profiles, and output patterns — and detect deviations from expected baselines."
You can explain every term in that sentence. That's the point.
§ 02 · Four Properties
Why this approach holds up under scrutiny
01
Actionable
You're not claiming to inspect the inside of the model — you're observing what the model does. That's a claim you can operationalise, instrument, and defend in front of regulators, auditors, and your own security team.
02
Model-Agnostic
Different providers expose different signals. Surface-based methods don't require uniform internals — they work at the boundary where all models make contact with your infrastructure, regardless of architecture.
03
Defensible
You can explain exactly what you're measuring and why deviations matter. That explainability is non-negotiable in regulated industries where 'the AI decided' is not an acceptable answer.
04
Enterprise-Friendly
Security teams care about observable behaviours against expectations — not abstract model internals. Surface detection fits the mental model they already use for every other monitored system.
§ 03 · Comparison
Surface-based vs output-only
§ 04 · See It In Practice
The surface is real.
So is the fingerprint.
Every model family has a distinct behavioural signature — flat plateaus, dense ripples, abrupt ridges. Arkheia learns each fingerprint, monitors it continuously, and alerts when it drifts.