Download as pdf
Download as pdf
You are on page 1of 5
Program| ‘Year of Study Semester Course Type MCA 2" IL Generic Course Course Full Title __| Applications of Al in cyber security Course Short Title | MCAICS Course Code MCAICS 302 Credits 4 |Course Objective © To know how AI can solve problems in the cyber security space. * To understand deep learning fundamentals from a security perspective © To understand Cyber Security Threats and the Development of Secure Software Course Outcomes (CO) / Learning Outcomes On successful completion of this course, the learner will be able to CO1 | Understand the role and applications of machine learning algorithms to detect and/or stop| the minutest behaviors of malware. CO2 _| Leam techniques of AI for system robustness and Al-powered attacks CO3 _| Study detailed analysis of real-world case studies co4 Implement a fraud prevention and detection system using machine learning BCA MAWT304: Advance Algorithm Sr. Subject Subject Title No. Code Total Marks 1 | MCAICS302 | Applications of AI in cyber security 100 Prerequisites: + Students must have knowledge of the fundamentals of AI, and machine learni ing algorithms. ‘+ Little experience in the security domains, such as cryptography, access control, operations security, etc Sr. Topic Details No. % Weightage No. of Sessions 1 Fundamentals of AI and CS 1.1 Introduction: Security measures in Computing 1.1.1 Elements, attributes 1.1.2 Types of Cyber Crimes and Criminals 1.1.3 Basie Security Terminology 1.14 Threats and Vulnerability 1.2 Machine Leaming Algorithms and usage 1.3 Impact of AI on Cybersecurity 1.4 Al Applications in Cybersecurity: Real-Life Examples 1.4.1 Security screening 14.2 Security & crime prevention 143 Analyze mobile endpoints 1.4.4 Al-powered threat detection 1.4.5 Detection of sophisticated cyber-attacks 1.4.6 Reducing Threat Response Time 15 Drawbacks and Limitations of Using Al for Cybersecurity 15 12 2 [Artificial Intelligence in Cybersecurity 2.1 Introduction 2.2 AI systems’ support for cybersecurity 2.2.1 Sys 2.2.2. System resilience 2.2.3. System response -m robustness resilience, and response 2.3 Al malicious uses 2.3.1 Expansion of existing threats 2.3.1.1 Characteristies of Al-powered attacks 2.3.2 Introduction of new threats 2.3.2.1 Deepfakes 2.3.2.2 Breaking CAPTCHAs 2.3.2.3 Swarming attacks 2.2.4 Major techniques in the use of AI for system robustness, 12 2.4 Swarming attacks Use cases for Al in cyber security 3.1 Threat Detection 3.2 Improving Authentication 3.3 Faster Threat Response 3.4 Social Engineering Detection 3.5 Vulnerability Assessment 3.6 User Behavior Modelling 3.7 Using ML against SMS Scams 3.8 AL-based Antivirus Software 3.9 Email Monitoring 3.11 Fighting threats with Al in cyber security 3.11 Using ML for Securing Mobile Endpoints 3.12 Examples of machine leaning in cybersecurity 3.12.1 Spear Phishing 12.2. Watering Hole 12.3. Webshell 12.4 Ransomware 3.12.6 Denial of service attack 12.7 DNS Poisoning 3 3 3 3.12.5. Remote Exploitation 3 3 3.12.8 Port Scanning 12 Fraud Detection USING Machine Learning Systems 4.1 The rule-based approach 4.2 ML-based fraud detection 4.3 Fraud scenarios and their detection 43.1 Insurance claims analysis for fraud detection 4.3.2 Anti-fraud solutions for medical claims and healthcare 4.3.3 Fraud prevention solutions in eCommerce 4.3.4 Fraud detection in banking and credit card payments 4.3.5 Preventing loan application fraud 4.3.6 Machine learning for anti-money laundering 4.4 Advanced fraud detection systems 44.1 Labeling data 44.2 Training a supervised model 443. Ensembling models 4.5 Supervised fraud detection methods 4.5.1 Random forest 4.5.2. Support vector machine 4.5.3. K-Nearest Neighbors 4.5.4 Neural networks and Deep Neural Networks 15 12 [Extra Reading: Machine leaning code for Detection systems along with, Jassification algorithms, training testing datasets ete. Learning Resources Reference Books Web References T. Gupta, Bri B., and Quan Z. Sheng, eds. Machine learning for computer and cyber security: principle, algorithms, and practices. CRC Press, 2019. 2, Machine Learning for cyber security, Publisher Packt, ISBN 9781789614671 Machine Learning for cyber security, Sstarcooks 4, Artificial Intelligence and Data Mining Approaches in Security Frameworks Editor(s): Neeraj Bhargava, Ritu Bhargava, Pramod Singh Rathore, Rashmi Agrawal, 2021 https:/link. springer. com/book/10.1007/978-3-319-98842-9 httos://doi.org/10.1155/2024/3329581 For code: https://github.com/packtpublishing/machine-learning-for-cybersccurity- cookbook Evaluation Details: Assignments + Attendance | Mid-Term-1] _ Midterm-2| End Term] Total 20% 10% 10% 60% 100 % Grading Scheme Min 85 and above Srade x Sacren 80 84 A 9 | 75 79 Be 3 B 70 74 B 7 ci 60 69 ce é c¢ | 50 | 59 c S a) 5 | F Below 40 Fail F oO

You might also like