Applying Intrusion Detection and Response systems for securing the Client Data Signals in the Egyptian Optical Network

Abstract

The physical layer of the Optical Transport Network (OTN) is the weakest layer in the network, as anyone can access the optical cables from any unauthorized location of the network and stat his attack by using any type of the vulnerabilities. The paper discusses the future role of the machine learning technology in the detection of the security threats and the automatic response to overcome the security challenges in the Egyptian optical network and it presents a new proposed model for the threats detection and the response to protect the client’s data on the physical layer of the optical network. The detections of the threats in the optical network will be done in our model by proposing learning algorithms from the continuous variations in the optical signal to noise ratio (OSNR) over the entire network and at the same time according to the past experiences of the proposed model it will decide if this variations are threats or normal attenuations on the optical cables. The response will be done by distributing the triggers for the encryption keys between the network elements according to the decisions of the intrusion detection system of the machine learning techniques. A new security layer will be established to the OTN frames in the infected sections only. The design of the proposed security model is done by using a structure of XOR, a Linear Feedback Shift Register (LFSR), Random Number Generator (RNG) associated with different techniques of learning algorithms, and expert system for the threats in the optical network. We propose the security model for different rates in the OTN and wavelength division multiplexing (WDM) system. The proposed model is implemented on the basis of protecting the infected sections in the physical layer only over the optical network by passing these signals into extra layer called security layer, and before forming the final frame of the OTN system, this done according to the decisions of our proposed security learning algorithms in the management layer of the optical network. The results show that using machine learning techniques in the proposed model of the OTN encryption scheme is providing a high security against any wiretapping attack and reduces the huge cost of implementing complete security algorithms over all the network sections without any benefits. Although the proposed model of the intrusion detection and response systems in the optical network will be implemented on the infected sections only the attacker who has the ability to access the fiber cables from any unauthorized location, will affect the OSNR value and as a consequences the system will detect this difference in the value of the OSNR and according to the past experience the system will response to this threat, the attacker will find encrypted data only and will take many years to find one right key to perform the decryption process