VPN detection for operators, ISPs and regulators
VPN detection for operators and regulators in Saudi Arabia
VPN detection means recognising VPN and other tunnelled traffic as a class of traffic on the network, so that reports show it and policies can refer to it. Interkey Intelligent DPI classifies VPN and tunnelled or evasive applications without decrypting them, using flow behaviour such as handshake structure, packet sizing and timing, and endpoint behaviour. It is built for network governance and regulatory compliance. It is not a tool for monitoring individuals. This page answers one question: what does VPN detection cover, who uses it, and what it leaves out.
A Saudi product, built by Interkey
For network, policy and compliance teams at operators and ISPs, and for regulators. Reviewed November 2026.
- What it is:classification of VPN and other tunnelled traffic as traffic classes, without decryption.
- What it does:identifies tunnelled flows from their behaviour, so reports include them and operator policy can refer to them.
- Who it is for:operators and ISPs in Saudi Arabia, and the regulatory teams that set their obligations.
- Where it works:fixed and mobile networks, on your own infrastructure; it can operate entirely in the Kingdom.
What VPN detection does, and what it does not
| Question | Answer |
|---|---|
| Does it decrypt traffic? | No. Traffic is not decrypted at any stage. Classification uses observable characteristics of the flow. |
| What does it produce? | A traffic class for each flow, shown in reports and available to operator policy. The output is metadata about applications, traffic volumes and triggered policies. |
| Does it act on its own? | No. Any action is set by your policy and applicable regulation, and a policy acts on traffic only in an inline deployment. |
| Is it a tool for monitoring individuals? | No. It is built and offered for network governance and regulatory compliance, and its reports describe classes of traffic and subscriber groups. |
Why VPN and tunnelled traffic is hard to detect
A tunnel wraps one flow inside another, so what an operator sees at first is the tunnel, not the application inside it. Encryption removes the payload signal, and tunnels often use the same common ports as everyday services. Classification by port number or payload alone therefore either misses tunnelled traffic or attributes it to the wrong class.
Some applications go further. VPN and other evasive applications keep changing to avoid detection, and disguise their traffic as legitimate services. For an operator this has two costs: traffic reports undercount what is really on the network, and any policy that refers to these classes acts on the wrong flows.
How Interkey Intelligent DPI detects tunnelled traffic
An AI traffic model built into the engine core combines several features of a flow rather than relying on any single one. Automated online probing extracts those features from live traffic, the model is retrained automatically, and Live View results feed back to refine models and policies. Because applications keep changing, detection is a process and not a one-time setting.
For the method in depth, see Encrypted traffic classification without decryption. For the operator view of VPN and tunnelled classes, see VPN and tunnelled traffic classification.
What operators and regulators use the result for
| Audience | Typical need | What the platform provides |
|---|---|---|
| Operators and ISPs | Reports that show tunnelled traffic instead of undercounting it, and policies that act on the right flows. | Classification of VPN and tunnelled flows, Live View trends and policy execution feedback. |
| ISPs applying national filtering requirements | In Saudi Arabia, CST supplies filtering lists to data service providers, who apply them on their internet gateways. Tunnelled traffic can carry applications the lists refer to. | Classification that includes tunnelled and evasive applications, a URL library, and report-only mode to check a rule before it acts. |
| Regulators | Evidence that rules are applied consistently, including to encrypted and evasive applications. | Classification of application traffic, policy execution feedback, and a reporting layer for regulatory teams. |
For the regulator view, see DPI for telecom regulators.
Measure it on your own traffic
Classifier results depend on subscriber mix, application mix, the share of encrypted traffic and how recently the classifier was updated. Evasive applications keep changing, so measure tunnelled classes on your own traffic and check again after significant updates.
1. Build a verified sample.Generate tunnelled and non-tunnelled traffic from known applications on devices you control.
2. Classify out-of-band.The platform receives a copy of traffic without touching the forwarding path.
3. Measure both errors.Record detection and false-positive rates for each tunnelled class. A false positive means a policy acts on traffic that was not tunnelled.
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. See Measuring DPI classification accuracy on your traffic.
Governance boundaries
- A basis for each rule.Tunnels also carry legitimate business connectivity, so a rule that refers to tunnelled classes needs a stated basis, an owner and a review route.
- Report-only first.A rule shows what it would have done before it acts. Inline enforcement follows only after classification has proven itself.
- Data rules.Retention and access for the metadata follow your data-governance rules and the contract. The platform runs on your infrastructure and can operate entirely in the Kingdom.
Detection and classification: the same engine, two different questions
Detection asks whether a flow is VPN or tunnelled traffic. Classification places every flow, tunnelled or not, in an application class. Interkey Intelligent DPI answers both from the same flow behaviour, so a tunnelled class appears in reports and in policies next to every other class. The difference is the question a team is trying to settle. A compliance team asks whether tunnelled traffic is present at all, and in which cells and subscriber groups. A network team asks which application classes make up the traffic on a link. A policy owner asks whether a rule that refers to a tunnelled class acts on the right flows. Each question needs its own evidence: counts of tunnelled flows by cell for the first, class shares in Live View for the second, and report-only results for the third. Agree which question comes first before the test starts, because it decides what you measure.
If you are looking for how tunnelled classes are used in reports and operator policy, read VPN and tunnelled traffic classification.
Questions about VPN detection
Does VPN detection mean decrypting traffic?
How accurate is it?
Does it monitor individual subscribers?
What can an operator do with the result?
Can we test it before enforcing anything?
How is it priced?
Proof of concept in three phases
Written acceptance criteria.Agree which rules are tested, on which traffic and subscriber groups, how results are measured and what counts as a pass.
Out-of-band classification against verified traffic.Measure false positives as carefully as detection for every class the rules depend on.
Report-only policy, then the inline decision.Each rule shows what it would have done; enforcement follows only after classification has proven itself.
Discuss VPN detection on your network
Tell us which tunnelled classes matter to you, whether you are an operator, ISP or regulator, and your timeline. Our team in Riyadh replies in Arabic or English.
- Our engineers read your request
- We agree the scope of a technical session
- You see the product on a use case you choose