DBATU · Third Year B.Tech Artificial Intelligence & Allied · NEP 2020
AI for Cybersecurity
26AFAIPE507 · Elective I · Semester V · 2 credits · Continuous assessment 20 + mid-semester 20 + end-semester 60
One of the Elective I options. The course page lists 3 lecture hours; the Elective I slot carries 2 credits.
Unit 1: Machine Learning in Cybersecurity
5 hoursAn overview of machine learning with cybersecurity use cases; classifying threats, attacks, vulnerabilities, malware and trojans.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Machine learning for cyber security
- Threats, attacks and malware types
Unit 2: Malware Classification
6 hoursClassifying malware with supervised and unsupervised learning from signatures and profiles; decision trees and context-based malicious event detection.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Malware classification with machine learning
- Malicious event detection with decision trees
Unit 3: Detecting Abnormal Behaviour
5 hoursTime-series analysis and ensemble models to detect deviation from normal behaviour; case studies in reconnaissance detection.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Time-series anomaly detection for security
- Reconnaissance and scanning
Unit 4: Network Anomaly and Intrusion Detection
6 hoursEfficient network anomaly detection; the stages of a network attack and countering them with deep neural networks; building intrusion detection systems.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Network anomaly detection with deep learning
- Firewalls and intrusion detection
- Building an ML-based intrusion detection system
Unit 5: Adversarial Attacks on ML Systems
5 hoursAdversarial attacks, model poisoning, black-box and white-box attacks; reading research on attacks on deep learning systems.
Examined in the 60-mark end-semester paper, and in the mid-semester exam if it is taught by then
- Adversarial attacks on machine learning models
- Model poisoning
- Black-box and white-box attacks
Unit contents are summarised from the official DBATU syllabus . AiCanCode.org is not affiliated with Dr. Babasaheb Ambedkar Technological University (DBATU).