Interkey Intelligent DPI

Encrypted traffic on operator networks

Deep packet inspection vs SSL inspection: classifying without decrypting

SSL inspection decrypts traffic so that an intermediate system can read its content, then re-encrypts it. That only works when the client device trusts the inspecting system's certificate. Deep packet inspection (DPI) classification, as Interkey Intelligent DPI does it, identifies which application an encrypted flow belongs to from characteristics that stay observable, and it does not decrypt. On an operator network, where the job is to know what the traffic is for capacity, policy and reporting, classification without decryption is the approach that fits.

A Saudi product, built by Interkey

For network and security engineers at telecom operators and ISPs. Reviewed November 2026.

  • SSL inspectiondecrypts, inspects content and re-encrypts, and it depends on client devices trusting the inspecting system's certificate.
  • DPI classification without decryptionidentifies the application class from handshake structure, packet sizing and timing, and endpoint behaviour.
  • On operator networkssubscriber devices are not managed by the operator, and the questions are about traffic classes, not content.
  • Interkey Intelligent DPI does not decrypt traffic.Its output is metadata about applications, traffic volumes and triggered policies.

Deep packet inspection vs SSL inspection, side by side

SSL inspection and DPI classification without decryption
SSL inspectionDPI classification without decryption
What it doesIntercepts the encrypted session, decrypts it, inspects the content and re-encrypts itIdentifies the application or protocol class of each flow
What it relies onClient devices that trust the inspecting system's certificateHandshake structure, packet sizing and timing, and endpoint behaviour
Does the content stay encrypted?No, it is decrypted at the inspection pointYes
What it producesInspected contentMetadata: applications, traffic volumes and triggered policies
Where it fitsNetworks whose owner manages the client devicesOperator networks carrying subscriber traffic

Why operators classify without decrypting

Subscriber devices are not managed by the operator.SSL inspection depends on each client device trusting the inspecting system's certificate. That condition holds on devices an organisation manages for its own staff. It does not describe subscriber devices on a national operator or ISP network.

The operator's questions are about traffic classes.Capacity planning asks which applications drive load. Policy asks which traffic a rule refers to. Regulatory reporting asks the operator to describe its traffic. None of these needs the content of a message, only the class of the flow.

Data governance is simpler when content is never exposed.Classification without decryption leaves encrypted content encrypted. The platform's output is metadata, its retention and access follow the operator's data-governance rules and the contract, and the platform can run entirely in the Kingdom.

The platform is built for governance, not surveillance.Interkey Intelligent DPI is built and offered for network governance and regulatory compliance, not for surveillance of individuals. Policies act per application, subscriber group or cell.

What stays observable when traffic is encrypted

Characteristics used to classify encrypted flows
CharacteristicWhy it helps
Handshake structureDifferent applications set up encrypted sessions in distinguishable ways
Packet sizing and timingVideo, messaging, calls, file transfer and tunnels produce different patterns
Endpoint behaviourApplications reach characteristic sets of services

An AI traffic model built into the engine core combines these features instead of relying on any one of them, and it is retrained automatically on features extracted from live traffic. The same approach applies to tunnelled flows. For the method in depth, see Encrypted traffic classification without decryption.

What classification without decryption does not do

  • It does not read content.It tells you the class of a flow, not what is inside it.
  • It does not decide what is permitted.That is set by your policy and applicable regulation.
  • Its accuracy is not a given.Results depend on subscriber mix, application mix, the share of encrypted traffic and how recently the classifier was updated. Measure detection and false-positive rates per class on your own traffic. See Measuring DPI classification accuracy on your traffic.

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, which is why we recommend measuring it on yours.

Test it on your traffic in 3 stages

  1. 1. Written acceptance criteria.Agree which encrypted application classes matter, on which traffic, how results are measured and what counts as a pass.

  2. 2. Out-of-band classification against verified traffic.The platform receives a copy of traffic without touching the forwarding path; measure false positives as carefully as detection.

  3. 3. Report-only policy, then the inline decision.Policies show what they would have done before they act; inline enforcement follows only after classification has proven itself.

See also: How Interkey runs a DPI proof of concept

Questions about DPI and SSL inspection

Does Interkey Intelligent DPI decrypt SSL traffic?

No. It classifies encrypted flows from observable characteristics such as handshake structure, packet sizing and timing, and endpoint behaviour. It does not decrypt traffic to classify it.

Is DPI the same as SSL inspection?

No. SSL inspection decrypts traffic to read its content. DPI classification as described here identifies the application class of a flow and leaves the content encrypted.

Which encryption protocols does it handle?

Coverage of the protocols and applications in your traffic is confirmed during the proof of concept, on your own traffic sample, rather than from a list.

Can it classify VPN and tunnelled traffic?

Yes. It classifies tunnelled flows as well as encrypted ones, including VPN and other evasive applications. What happens to that traffic is set by your policy and applicable regulation. See VPN & tunnelled traffic classification.

Does it support national content-filtering requirements?

Application classification and content filtering for regulatory compliance are among the needs Interkey Intelligent DPI is built for at ISPs. Classification does not decrypt traffic; how a filtering requirement translates into policies is defined during scoping. See ISP content filtering for national requirements.

Do we need an inline deployment to test it?

No. Out-of-band deployment gives classification and reporting. Only policy enforcement needs an inline deployment.

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

Test classification on your traffic

Tell us which encrypted application classes matter to you, roughly what share of your traffic is encrypted (if known), 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.