A Comparative Study on Deep Learning-Based Algorithms For Intruder Detection Systems and Cyber Security

Abstract

For data protection, the most vital factors are the statistics' safety, use of cryptographic controls during data transmission, an effective access management system, and powerful tracking. This paper seeks to provide a committed evaluation of the very current studies works on using Deep studying strategies to remedy computer security demanding situations. In this study, we analyzed and reviewed using deep learning algorithms for the Intruder detection system and Cybersecurity programs. Deep learning consists of system-mastering strategies that permit the network to learn from unsupervised data and solve complicated problems. Deep learning approaches such as Convolutional Neural Network (CNN), Auto Encoder (AE), Deep Belief Network (DBN), Recurrent Neural Network (RNN), Generative Adversal Network (GAN), and Deep Reinforcement Learning (DIL) are used to categorize the papers referred. This paper discusses various challenges, issues, and types of cyber-attacks and security measures