The institution's rules
Amounts, merchant categories, countries and time windows your team defines from the console, each amount in its own currency.
Cortex Shield · card fraud prevention
Shield scores every card purchase and answers approve, review or decline, with its reasons. It is installed in the institution's own data center, and the institution stays in charge: Cortex decides, explains and alerts; it does not block cards or touch the core.
Incoming purchase
Cortex's answer
Review
Cortex Shield
The institution's switch sends each purchase to Cortex as JSON, with the ISO 8583 fields it already handles. Cortex scores it and answers with a decision and its reasons. The institution stays in control: Cortex decides, explains and alerts; it does not block cards or touch the core.
The switch sends the authorization. The card number is replaced by a token as soon as it comes in, and the original is discarded.
The institution's rules, usage velocity, that card's habits and a model trained on the bank's own history.
Approve Review Decline with its reasons; those of the rules, in plain language. Whatever goes to review reaches the analyst's queue with its case file.
Amounts, merchant categories, countries and time windows your team defines from the console, each amount in its own currency.
Recognizes card testing by CVV2 or expiry checks that keep failing: many cards at one merchant, or one card across several merchants.
A per-card memory learns, from every purchase Shield does not decline, where, how much and how its cardholder buys, without waiting for a retraining.
Trained on the institution's labeled history. It can start in shadow mode: it reports its opinion alongside each decision without changing it.
A chip card that comes in by magnetic stripe is a signal of its own. On top of that, the card's memory notices a channel or a way of reading the card that doesn't fit the cardholder's habits.
The same card used in person in several countries within a short window, which the institution sets in its rules.
When several cards with fraud went through the same merchant, it flags it as a possible origin and lists the exposed cards.
Analyst queue with the case file for each alert. A confirmed chargeback corrects what the card had learned.
Email with the server's certificate verified whenever it goes over TLS, never sending a password unencrypted, and webhooks signed under the open Standard Webhooks specification, configurable from the console.
Performance
Shield runs on commodity servers and returns each decision with its reasons. How it performs under your institution's load is not promised from a web page: it is measured on your own hardware.
It answers while the purchase is being authorized. In the lab it does so in a few milliseconds; the time under each institution's load is measured on its server.
Runs on standard x86 processors, in podman containers on a Linux server. Capacity is measured with each institution's hardware and traffic.
Approve, review or decline: every answer carries its written reasons and is recorded, for the analyst and for audit.
It remembers how each cardholder buys and updates with every purchase Shield does not decline, to tell the usual from the unusual.
How we measure: Today's measurements come from the lab, with simulated purchases, which is why this page publishes no detection or capacity figures. The ones that count are those obtained with each institution's data and hardware, through a procedure that can be repeated.
Shield does not replace rules or trained models: it combines them with a per-card memory. Each approach covers what the others find hard.
| Criterion | The institution's rules | Model trained on history | Per-card memory |
|---|---|---|---|
| What it needs to start | Someone who knows the fraud and writes the rules | History with the fraud already identified | Each card's first purchases |
| How it keeps up to date | By hand, rule by rule | By retraining every so often | On its own, with every purchase Shield does not decline |
| What it explains about a decision | Which rule fired | A risk score | Where the purchase departed from that card's habits |
| Where it struggles | Fraud nobody anticipated | Cards with no history and fraud unlike the training data | The cardholder who changes habits, as on a trip |
| In Cortex Shield | Your team defines them from the console | Trained on the institution's history of confirmed fraud | Updated with every purchase it does not decline, with no retraining |
Security
On top of Cortex's shared controls: your own perimeter, keys under custody, roles, audit, retention and TLS. See the shared controls →
On arrival it is replaced by an HMAC-SHA256 token with the institution's own key. Expiry date, CVV2, PIN and track data are not stored either: only the result of their verification.
If the license expires, everything keeps working for a 30-day grace period. After that, Shield keeps scoring purchases and alerting, and the console keeps people, roles, audit and retention; the model stops retraining and the rest of the console waits for the renewal. Nobody is left without detection because of paperwork.
Because Cortex recommends and the institution decides, it can run alongside the current authorization and be measured with your own data before it influences anything.
Frequently asked questions
No. It returns a recommendation with its reasons and the institution's authorizer decides what to do with it. Cortex does not touch the core or change the status of any card.
The switch sends each authorization as JSON with the ISO 8583 fields it already handles.
In two ways. Each card has a memory that is updated with every purchase Shield does not decline. Separately, the supervised model is trained on the institution's own history of confirmed fraud, and can first run in shadow mode.
Yes. Since the final decision belongs to the institution, Cortex can run in parallel with the current authorization and be measured with your own data before its answer is used.
We arrange a demo and a trial in parallel with your current authorization.