View source for 17957337. INTERNET OF THINGS (IOT) DEVICE IDENTIFICATION USING TRAFFIC PATTERNS simplified abstract (Fortinet, Inc.)

=INTERNET OF THINGS (IOT) DEVICE IDENTIFICATION USING TRAFFIC PATTERNS=


==Organization Name==

[[:Category:Fortinet, Inc.|Fortinet, Inc.]]


[[Category:Fortinet, Inc.]]

==Inventor(s)==

[[:Category:Haitao Li of Coquitlam (CA)|Haitao Li of Coquitlam (CA)]][[Category:Haitao Li of Coquitlam (CA)]]

==INTERNET OF THINGS (IOT) DEVICE IDENTIFICATION USING TRAFFIC PATTERNS - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17957337 titled 'INTERNET OF THINGS (IOT) DEVICE IDENTIFICATION USING TRAFFIC PATTERNS

==Simplified Explanation==

The patent application describes a method for identifying devices based on flow pair values and device types.

* Flow pair values are identified by comparing individual flows of unknown devices to labeled devices.
* Device candidates are determined based on flow pair values surpassing a threshold.
* A difference flow matrix is generated to compare flows of unknown and labeled devices.
* Known devices are identified as candidates based on the sum of flow pair values.
* Device types are retrieved for each candidate device, and one is selected based on closeness or frequency to the unknown device.

== Potential Applications ==
This technology could be applied in network security to identify unknown devices and classify them based on their behavior.

== Problems Solved ==
This technology solves the problem of accurately identifying devices on a network without prior knowledge or manual intervention.

== Benefits ==
The benefits of this technology include improved network security, automated device identification, and efficient device classification.

== Potential Commercial Applications ==
A potential commercial application of this technology could be in the development of network security products for enterprises.

== Possible Prior Art ==
One possible prior art could be methods for device identification based on flow analysis in network traffic monitoring systems.

=== What are the limitations of this technology in identifying unknown devices on a network? ===

The technology may face limitations in accurately identifying devices that have similar flow patterns or behaviors, leading to potential misclassifications.

=== How does this technology compare to existing methods of device identification in terms of accuracy and efficiency? ===

This technology offers a more automated and efficient approach to device identification compared to traditional methods that rely on manual inspection or predefined rules.


==Original Abstract Submitted==

Flow pair values are identified from flow pairs of labeled devices as candidates by comparing individual flows of the unknown device that surpass a candidate threshold by generating a difference flow matrix from the individual flows of the unknown device and the labeled device. Known devices can be identified as device candidates from a sum of flow pair values for each candidate device in relation to the unknown device. A device type can be retrieved for each candidate device, and one of the device types can be selected based on at least a closeness or a frequency of each device type to the unknown device.



[[Category:H04L9/40]]