Unit 1 Machine Learning and Cyber Security Cyber threat landscape,

• The cyber attacker’s economy
• A marketplace for hacking skills
• Indirect monetization
• The upshot
• Adversaries using machine learning
• Real- world uses of machine learning in security
• Spam Fighting: An iterative 08 20 GUJARAT TECHNOLOGICAL UNIVERSITY Program Name: Master of Engineering Level: PG Branch: Cyber Security Subject Code : ME02059041 Subject Name : Artificial Intelligence in Cyber Security –Part II w.e.f. 2024-25 https://syllabus.gtu.ac.in/ Page 2 of 3 approach
• Limitations of machine learning in security
• Machine Learning: problems and approaches
• Machine Learning in practice: A worked example
• overview of classification and clustering

Unit 2 Anomaly Detection using Artificially Intelligent Methods

8 lecture hours

• When to use anomaly detection versus supervised learning
• Intrusion detection with heuristics
• Data-driven methods
• Feature engineering for anomaly detection
• Host intrusion detection
• Network intrusion detection
• Web application intrusion detection
• Anomaly detection with data and algorithms
• Forecasting (supervised machine learning)
• Statistical metrics
• Unsupervised machine learning algorithms
• Density-based methods
• Challenges of using machine learning in anomaly detection
• Response and mitigation
• Practical system design concerns
• Optimizing for explainability
• Maintainability of anomaly detection systems
• Integrating human feedback
• Mitigating adversarial effects

Unit 3 Network Traffic Analysis using Artificially Intelligent

8 lecture hours

• Methods Theory of network defense
• Access control and authentication
• Intrusion detection
• Detecting in-network attackers
• Data-centric security
• Machine learning and network security
• From captures to features
• Threats in the network
• Botnets and you, Building a predictive model to classify network attacks
• Exploring the data
• Data preparation
• Supervised learning
• Semi-supervised learning
• Unsupervised learning
• Advanced ensembling

Unit 4 Protecting the Consumer Web Monetizing the consumer web,

7 lecture hours

• Types of abuse and the data that can stop them
• Authentication and account takeover
• Account creation
• Financial fraud
• Bot activity
• Supervised learning for abuse problems
• Labeling data
• Cold start versus warm start
• False positives and false negatives
• Multiple responses
• Large attacks
• Clustering abuse
• Example: clustering spam domains
• Generating clusters
• Scoring clusters
• Further directions in clustering

Unit 5 Adversarial Machine Learning Terminology, The importance

• of adversarial ML, Security vulnerabilities in machine learning algorithms
• Attack transferability
• Attack technique: model poisoning
• Example: binary classifier poisoning attack
• Attacker knowledge
• Defense against poisoning attacks
• Attack technique: evasion attack
• Example: binary classifier evasion attack
• Defense against evasion attacks. 08 15 6 UNIT VI: Recent Trends in AI for Cyber Security. 04 05