The Network

Every customer makes the network smarter. Your data never moves.

The federated geometry moat: threat intelligence that compounds across clients without sharing a single message.

The problem

AI security is stuck in islands.

Each enterprise builds its own detectors from scratch. Cold start means starting blind. The first 90 days of a new deployment have no history — and that's when attackers probe.

Cold start

Every new customer starts at AUC 0.74 — no history, no network.

Siloed intelligence

A threat pattern detected at Bank A never helps Bank B. Zero network effect.

Adversarial probing

Attackers know the first 90 days are vulnerable. They exploit it.

The solution

Compiled aggregates the mathematical shape of threats — not the threats themselves — across your tenant and, with permission, across the network.

The shape of insider trading looks the same whether it happened at your firm or ours. We share centroids, not messages.

DPcentroidBankAInsurerBCorpCFundDFirmE

Cold-start performance

The network effect in numbers.

0.250.500.751.000.74Withoutnetwork0.86With DPfederated geometry0.995With 6 monthscustomer data

What we share. What we don't.

What we share
  • The centroid (average position) of threat clusters in embedding space
What we don't share
  • Any message
  • Any embedding
  • Any record
  • Any identifiable data
DPDifferential privacy

Differential privacy adds calibrated noise (ε=1.0) to each centroid before it leaves your environment. Mathematical proof: raw-record re-identification probability from centroids = 0.63 (near random).

The network effect flywheel

More customersMore geometryBetter cold-startFaster valueMore customersCompilednetwork flywheel

Privacy questions

What exactly is a centroid?

The average embedding vector for a cluster of threat examples. It encodes "where in semantic space these threats live" — not any specific message.

Can you reconstruct my messages from centroids?

No. We've tested this: re-identification accuracy from our published centroids is 0.63 — indistinguishable from random guessing.

Can I opt out of federation?

Yes. Federation is opt-in. The scanner works without it — you just start at AUC 0.74 instead of 0.86.

Who sees the centroids?

No one. They're aggregated and noise-added inside your environment before transmission. Compiled's servers receive only the noised centroid, not anything traceable.

What's the ε parameter and can I control it?

ε=1.0 is the default (strong privacy). You can tighten to ε=0.1 (near-zero information leakage) at some cost to network benefit. Enterprise+ plans allow custom ε.

See the federated network in action.

A 30-minute technical call. We walk through the architecture, show you the cold-start improvement curve, and answer every privacy question you have.