Security Analysis of Attacks in SDN Based Smart Grids Network using Machine Learning and Deep Learning Techniques - Master of Science Thesis

Aug 5, 2026

Cybersecurity becomes increasingly critical as technology advances, while cybercriminals develop sophisticated attack techniques that can severely affect organizations. This thesis examines how AI, Machine Learning (ML), and Deep Learning (DL) support intrusion detection and defense by analyzing patterns and anomalies in network traffic, system logs, and user behavior. It highlights anomaly detection, threat intelligence, predictive deep models for proactive attack identification, and endpoint security using behavioral analysis and malware detection.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages85

Reading Time3 h 34 min

AccessFree to download

Table of Contents

List of Figures

Chapter 1 | Introduction to Cyber Attack

1.1 | Introduction

1.2 | Different Cyber Attacks

1.3 | Role of Machine learning and deep learning in preventing Cyber attacks

Security Analysis of Attacks in SDN Based Smart Grids Network using Machine Learning and Deep Learning Techniques by Ashish Under supervision of supervisor Dr. Parveen Malik A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Internetworking Department of Electrical and Computer Engineering University of Alberta © Ashish, 2023 Abstract Cybersecurity is becoming increasingly critical as the world continues to advance in technology. As a result, cybercriminals are finding new and sophisticated ways to launch cyber attacks on organizations, which can have severe consequences. In recent years, Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) have shown enormous potential in detecting cyber attacks, making them a vital aspect of cybersecurity. Artificial Intelligence (AI) is a branch of computer science that deals with the development of intelligent machines that can mimic human behavior. Machine Learning (ML) is a subset ofAI that focuses on creating algorithms that enable machines to learn from data and make predictions without being explicitly programmed. Deep Learning (DL) is another subset of AI that uses artificial neural networks (ANN) to learn and analyze data. AI, ML, and DL are useful in detecting cyber attacks because they can analyze vast amounts of data and identify patterns and anomalies that are difficult for humans to detect. Cyber attackers use different techniques to carry out cyber attacks, such as malware, phishing, brute force attacks, and SQL injection. AI, ML, and DL can be used to detect and prevent these attacks by analyzing various data sources, such as network traffic, system logs, and user behavior. One of the most significant applications of AI, ML, and DL in cybersecurity is in anomaly detection. Anomaly detection is the process of identifying unusual patterns or behaviors that deviate from the norm. Cyber attackers often use new and sophisticated techniques that traditional cybersecurity systems may not detect. AI, ML, and DL can be trained to recognize patterns and behaviors that are outside the norm and flag them as potential threats. For example, AI-based intrusion detection systems (IDS) can learn normal network traffic behavior and identify any anomalous traffic patterns. Another application of AI, ML, and DL in cybersecurity is in threat intelligence. Threat intelligence involves gathering, analyzing, and sharing information about potential cyber threats. AI, ML, and DL can be used to collect and analyze data from various sources, such as social media, dark web forums, and malware repositories, to identify potential threats. Machine learning algorithms can also learn from historical data to identify common patterns and indicators of past attacks and use that knowledge to prevent future attacks. Cyber attackers often use social engineering techniques, such as phishing, to trick users into revealing sensitive information or downloading malware. AI, ML, and DL can be used to detect phishing attempts by analyzing email content, links, and sender information. Machine learning algorithms can also learn from past phishing attempts to identify common patterns and indicators of phishing attacks and use that knowledge to prevent future attacks. Deep Learning can be used in cybersecurity to develop predictive models that can identify attacks before they happen. This is achieved by using Artificial Neural Networks to analyze large datasets to identify patterns and relationships between different data points. Deep learning models can be trained on large amounts of data, and can then predict future attacks based on this information. For example, deep learning models can be trained to analyze network traffic patterns and detect malicious activity, such as DDoS attacks, before they occur. AI, ML, and DL can also be used in endpoint security to detect and prevent malware attacks. Endpoint security involves

FAQs

How do AI, ML, and DL help detect cyber attacks in this thesis?

They analyze large volumes of data to identify patterns and anomalies that are difficult for humans to detect, using inputs such as network traffic, system logs, and user behavior.

What cybersecurity applications are emphasized besides anomaly detection?

Threat intelligence and phishing detection are emphasized, using historical data and analysis of email content, links, and sender information.

How can deep learning models be used for predicting attacks before they occur?

Deep learning models analyze large datasets with artificial neural networks to learn relationships in network traffic and predict future malicious activity, including DDoS attacks.

Aug 5, 2026

Upload by Seraphina