Algorithm for identifying clients based on dynamic MAC addresses in narrowly targeted secure networks using deep learning neural networks

Abstract

Existing algorithms for identifying clients on a network segment are based on static client binding by MAC address. MAC address generation is based on pseudo-random sequences of 0–256 characters. With this feature in mind, software was developed based on an algorithm for generating MAC addresses using bidirectional neural networks, followed by integration of a decision support system module. A secondary feature of the developed software is the ability to set a MAC validity timeout, which will limit access to the network segment and increase the security factor.

Keywords:

• MAC address
• neural network
• fuzzy logic
• device identification
• information security

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

The reported study was funded by Russian Foundation for Basic Research (RFBR) according to the research project No. 20-37-90062.