Interkey Intelligent DPI

Testing and acceptance

Measuring DPI classification accuracy on your traffic

Measure DPI classification accuracy per application class, on a sample of your own traffic where you already know the right answer, and report both detection and false positives for each class rather than one headline figure. Any accuracy figure a vendor quotes is a starting point: subscriber mix, application mix, the share of encrypted traffic and how recently the classifier was updated all change the result. This page sets out a method your test and acceptance team can use.

A Saudi product, built by Interkey

For test, acceptance and network engineering teams at telecom operators, ISPs and regulators. Reviewed November 2026.

  • Per class, not one number:detection and false positives for every application class that matters to you.
  • On your traffic:a classifier tuned on one operator's traffic will not behave identically on another's.
  • Against verified ground truth:traffic generated by known applications on devices and subscriptions you control.
  • Out-of-band, and repeated:test without touching the forwarding path, and re-test after significant updates.

Why one accuracy number is not enough

A single figure averages over every class. If a few large classes are classified well, the average can look high while the classes your policies depend on are classified poorly. It also says nothing about false positives: traffic wrongly placed in a class. A false positive matters as much as a miss, because it means a policy acts on the wrong traffic.

DPI classification accuracy: the measures to report

Classification accuracy measures
MeasureWhat it tells youWhy it matters
Detection rate (per class)Of the traffic that truly belongs to a class, the share the engine placed in that classShows what a policy or report on that class would miss
False positives (per class)Traffic from other classes that the engine placed in this classShows what a policy on that class would wrongly act on
Precision (per class)Of everything the engine placed in a class, the share that truly belongs thereCombines both effects into what the class label is worth
Unclassified shareTraffic the engine did not assign to any classShows how much traffic sits outside every policy and report
Confusion between classesWhich classes are mistaken for whichPoints to the classes that need attention
Stability over timeWhether results hold after updates and as applications changeShows whether today's result will still hold next month

Decide in advance whether you count flows or bytes. Both are valid, but they give different answers: a few large flows can dominate a byte count.

Building a verified sample

Ground truth is traffic where you know the right answer independently of the engine under test.

  • Generate it yourself.Run known applications on devices and subscriptions you control, so the sample contains no subscriber data and every flow has a known label.
  • Cover the classes that matter.Include every class your policies and reports depend on, and the encrypted and tunnelled versions of them.
  • Include changing applications.Use current application versions, and repeat later with newer versions.
  • Keep it separable.Make sure the sample can be told apart from other traffic in the results, for example by the test devices' addresses.
  • Test at realistic load.Run part of the test during your busy hour, so the engine is measured under the load it will face.

The test method, step by step

  1. 1. Write the acceptance criteria first.For each class, agree the detection and false-positive thresholds, the unit (flows or bytes) and the reports to be produced, before the test starts.

  2. 2. Classify out-of-band.The platform observes traffic without sitting in the forwarding path, so the test cannot affect subscribers.

  3. 3. Compare with ground truth.For each class, count correct results, misses and false positives, and record the unclassified share.

  4. 4. Report per class.Produce the measures above for every class, with the confusion between classes.

  5. 5. Repeat after updates.Re-run the test after significant model or policy updates, and on a regular schedule as applications change.

Setting thresholds by what the class is used for

The threshold for a class should follow what will be done with it:

How strict a threshold should be
Use of the classThreshold emphasis
Reporting and capacity planning onlyDetection and the unclassified share, so trends are reliable
A policy in report-only modeBoth measures, to see what the rule would have done
A policy that acts on traffic, such as blocking where your policy and applicable regulation require itThe strictest false-positive limit, because a false positive acts on the wrong traffic

On Interkey's accuracy figure

Interkey's product material states 99% recognition accuracy, including for VPN and other adversarial encrypted applications. The figure has not been independently benchmarked and is not a specification for any particular network. Results depend on subscriber mix, application mix, the share of encrypted traffic and how recently the classifier was updated, which is why we recommend measuring it on your traffic with the method above.

Interkey Intelligent DPI classifies from flow behaviour (handshake structure, packet sizing and timing, and endpoint behaviour) without decrypting traffic. Its model is retrained automatically on features extracted from live traffic, and Live View results feed back into models and policies, so re-checking accuracy after significant updates belongs in your change control. More on the engine: Network traffic classification engine for telecom operators.

Where this fits in a proof of concept

This method is the second of the three proof-of-concept stages Interkey recommends: written acceptance criteria first; out-of-band classification measured against verified traffic, with false positives measured as carefully as detection; then policies in report-only mode before the inline decision. How Interkey runs a DPI proof of concept

To make the method binding in a tender, see the DPI RFP requirements checklist.

Questions about DPI accuracy testing

How do you measure DPI classification accuracy?

Classify a verified sample of your own traffic out-of-band, compare the results with the known labels, and report detection, false positives and precision for each class, plus the unclassified share.

What is a false positive in DPI?

Traffic that the engine places in a class it does not belong to. If a policy acts on that class, it acts on the wrong traffic.

Why do results differ between networks?

Subscriber mix, application mix, the share of encrypted traffic and how recently the classifier was updated all differ between networks, and all of them affect the result.

Can we test without affecting subscribers?

Yes. Out-of-band classification observes traffic without sitting in the forwarding path, and a sample generated on devices you control contains no subscriber data.

How often should accuracy be re-tested?

After significant model or policy updates, and on a regular schedule agreed in your acceptance criteria, because applications keep changing.

Proof of concept in three phases

  1. Written acceptance criteria.Agree which rules are tested, on which traffic and subscriber groups, how results are measured and what counts as a pass.

  2. Out-of-band classification against verified traffic.Measure false positives as carefully as detection for every class the rules depend on.

  3. Report-only policy, then the inline decision.Each rule shows what it would have done; enforcement follows only after classification has proven itself.

Discuss a proof of concept on your network

Plan an accuracy test on your traffic

Tell us which application classes matter for your policies and reports, whether you already have a verified sample, and your timeline. Our team in Riyadh replies in Arabic or English.

  1. Our engineers read your request
  2. We agree the scope of a technical session
  3. You see the product on a use case you choose

Tell us your network type (mobile, fixed, ISP), approximate traffic volume and the use case you are evaluating.

By sending this form, you agree to our Privacy Notice.