Deep Learning for CyberSecurity
Overview
Deep Learning For CyberSecurity
Deep learning, a subfield of AI based on multiple layers of artificial neural networks, has established a key role in solving complicated cybersecurity problems due to its ability to manage complex data structures, its automatic feature extraction, and its efficiency in recognizing patterns and correlations
Swetha A
CSE
Register number: JU2023RPHD10145
SYNOPSIS
Title of research:
Deep learning for Cybersecurity
Introduction:
Cybersecurity mainly deals with protecting the critical systems and sensitive information from digital attacks. Types of attacks usually seen are malware, data breach, phishing, denial-of-service (DOS), social engineering etc. Many organizations deploy Cybersecurity for their databases and systems to prevent it from unauthorized access. Deep learning is a method of machine learning based on artificial neural networks (ANN) which are designed to mimic the functionality and connectivity of neurons in human brain and in deep learning the number of layers within an ANN defines the depth of network. Deep Learning algorithms can be used for the Cybersecurity of unsupervised data by passing the input data through the layers of network and recognize the attacks.
Problem Statement:
Deep learning algorithms 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) can be used for Cybersecurity instead of traditional organization protection.
Objectives:
- List Deep learning algorithms used for Cybersecurity (Confidentiality, Integrity and Availability).
- On effectiveness of these algorithms.
- Focus on Intrusion Detection and Prevention system, dealing with malware, Network traffic analysis.