Skip to content
Visork
Request pilot access

Catching what hash databases can't see.

Visork is an ML-first classifier. Trained to recognise CSAM — including new and AI-generated material — in real time, inside your upload pipeline.

One model in production · More on the roadmap
<200ms
End-to-end response target
EU only
Inference, storage, audit
ML-first
Catches novel and AI-generated content
Explorerscore · threshold · verdict
Scenario

Score well above threshold — clear block.

Verdict
block
Score 0.974Threshold 0.85
What you'd ship

Score 0.974 against a 0.85 threshold. Visork returns a block verdict — engineered for sub-200 ms — with a signed audit log id.

Threshold tunable per module
Every analysis logged for audit
ML-FIRST, NOT HASH-FIRST

Two ways to detect harm.
Visork is the second one.

Hash matching is fast but only finds files that already exist in a database — it can't see new uploads or AI-generated material. The Visork ML classifier costs roughly ten times a hash lookup — still inside the sub-200 ms end-to-end target — and in exchange it works on content nobody has ever indexed. The two are complementary; the right answer for most platforms is to run them side by side.

upload.jpg · hash a3f4·8b91
Compare against known database
a3f4 · 8b91 · 0c2d · 4e17 Miss
9f8e · 3b22 · 4d70 · 6c19 Match
0b71 · 4f2a · d5c8 · e303 Miss
Latency
~20 ms
Coverage
Known files only

Hash matching (industry)

Detects only what's been seen before. Requires access to authorised hash databases (NCMEC, IWF) which are gated.

A note on thresholds

You set the threshold per module to fit your platform's risk profile. The verdict is a recommendation; the action — block, quarantine, review, allow — is yours.

THE BASE RATE

One upload in a hundred thousand.

Take the illustrative base rate from our explainer: one upload in a hundred thousand is abuse material. At that rarity nobody finds it by looking, and a vendor's “accuracy” figure stops meaning anything — a classifier that flags nothing at all scores 99.999 %. Visork returns a probabilistic score for every image and is measured on precision and recall, on your own traffic, during the pilot's 100 free analyses.

A note on accuracy

We don't quote an accuracy number.

We report precision and recall at a stated threshold, measured on your traffic — not on a curated test set where positives are a tenth of the data and every figure collapses on contact with a real upload stream.

Why “99 % accurate” tells you nothing
The two numbers that matter
Precision
Of everything flagged, how much was actually abuse material. Your review queue feels it.
Recall
Of the abuse material present, how much was caught. Your legal exposure feels it.
Threshold sets the trade-off · agreed per module during scoping

What's live today. What's next.

The same architecture extends across modules. We ship them one at a time — accuracy first, then coverage.

Liveyou are here
Roadmap
CSAM (images)
Live

Live with pilot platforms. Trained for novel and AI-generated content.

Violence
Roadmap

Same architecture, separate module.

Deepfakes
Roadmap

Detection of AI-generated impersonation imagery.

Nudity
Roadmap

General explicit-content detection alongside CSAM.

Grooming (text)
Roadmap

Conversational risk detection over chats and comments.

Modules ship once accuracy is calibrated · Order and dates under NDA

See it on your data.

Pilots start with 100 analyses at no cost, benchmarked against your own traffic rather than our demo set.

100 credits included · EU-hosted · Onboarded selectively