Hybrid Optimization Enabled Robust CNN-LSTM Technique for Network Intrusion Detection

Abstract

Nowadays, computer networks and the Internet are unprotected from many security threats. Introducing adaptive and flexible security-related techniques is challenging because of the new types of frequently occurring attacks. An intrusion detection system (IDS) is a security device similar to other measures, including firewalls, antivirus software, and access control models devised to strengthen communication and information security. Network intrusion detection system (NIDS) plays a vital function in defending computer networks and systems. However, several issues concerning the sustainability and feasibility of existing techniques are faced with recent networks. These concerns are directly related to the rising levels of necessary human interactions and reducing the level of detection accuracy. Several approaches are designed to detect and manage various security threats in a network. This study uses Chimp Chicken Swarm Optimization-based Deep Long Short-Term Memory (ChCSO-driven Deep LSTM) for the intrusion detection process. A CNN feature extraction process is necessary for effective intrusion detection. Here, the Deep LSTM is applied for detecting network intrusion, and the Deep LSTM is trained using a designed optimization technique to enhance the detection performance.

An efficient and secure key management with the extended convolutional neural network for intrusion detection in cloud storage

“…From the above discussed paper, 15,[22][23][24][25][26] several problems are noted: Several classifiers with several optimizations were used, but does not provide sufficient accuracy and possess high computational time with higher error rate.…”

“…Step 2: Random generation Following Initialization process, the populations of coot population(i) for attaining best solution are randomly generated and its equation is given in (15),…”

“…The NSL-KDD, CSE-CIC-IDS2018, UNSW-NB15 and ToN-IoT datasets are utilized for evaluating the average intrusion detection rate of the proposed Hyb EESCCNN. Then the efficiency of the proposed Hyb EESCCNN technique is likened by the previous technique such as SSA-DBN, 23 MLPNN-ABC, 24 ChCSO-driven deep LSTM, 15 CNN-CapSA, 26 respectively.…”

“…Similarly, non-malicious attacks of the proposed method attain 34.75%, 21.86%, 33.86%, 16.86% higher accuracy, 25.86%, 28.97%, 16.86%, 22.86% higher precision, 25.86%, 34.86%, 26.86%, 22.86% higher f-score than the previous methods. 23 MLPNN-ABC, 24 ChCSO-driven deep LSTM, 15 CNN-CapSA, 26 respectively.…”

“…This paper proposes a novel DL model Hyb EESCCNN optimized with Improved COOT Optimization Algorithm (ICOA) and is proposed for detecting intrusion in cloud system. It is the combined form of CNN 15 with Enhanced Elman spike neural network (EESNN) 16 and ICOOT 17 . Furthermore, a novel ATBGVHE method is proposed for providing the security of the system.…”