COMPUTER SCIENCE AND ENGINEERING DEPARTMENT
IIT Kanpur
CS 973: Machine Learning for Cyber Security
Instructor:
Dr. Sandeep K. Shukla
Computer Science and Engineering Department
Major, Measurable Learning Objectives
Having successfully completed this course, the student will be able to:
- Articulate and explain which problems in Cyber Security may be solvable with Machine Learning
- Understand and implement machine learning algorithms and models for Cyber Security problems such as malware analysis, intrusion detection, spam filtering, fraud detection, online behavior analysis etc
- Get basic hands on experience with supervised, unsupervised learning methods
- Understand basic theory of classification and regression techniques
- Understand feature extraction from data
- Develop tools for cyber defense using machine learning
- Prerequisites and Co-requisites
Must have completed the course on Introduction to Linear Algebra and have basic familiarity with probability theory.
- Texts and Special Teaching Aids
There is no specific text. Course notes, lecture notes, and projects will be available on the course website.
- Syllabus
Here is a tentative syllabus for the course -- but this is not set in stone. Some topics may be excluded, and some other topics may be included depending on the progress of the course.
- Data processing, cleaning, visualization, and exploratory analysis
- Data set collection and feature extraction
- Cyber Security problems that can be solved using Machine learning
- Malware Analysis, Intrusion Detection, Spam detection, Phishing detection, Financial Fraud detection, Denial of Service Detection
- Basic Probability theory and Distributions
- Estimation Theory, Hypothesis testing
- Linear Regression (uni- and multi-variate) and Logistic Regression
- Basic Classification Techniques
- Unsupervised Learning
- Supervised Learning
- Spectral Embedding, Manifold detection and Anomaly Detection
- Decision Trees
- Ensemble learning
- Random Forest
Lecture Plan
Module |
Topic |
No. of Hours |
Introduction |
Cyber Security Problems and Machine Learning Based Solutions |
1 |
Basic Probability and Distributions |
Binomial, Poisson, Normal, Exponential, other distributions
|
1 |
Estimation Theory and Hypothesis Testing |
Sampling, Estimation, Hypothesis testing |
2 |
Regression |
Uni- and multi-variate regression, logistic regression |
2 |
Supervised Learning
|
Linear Classifiers, Decision Trees, Ensemble Learning, Random Forest
|
3 |
Unsupervised Learning |
Clustering, Manifold Discovery, Diffusion map, spectral embedding, Anomaly detection, outliers |
5 |
Malware Analysis |
Static and Dynamic Analysis, Models that work well |
2 |
Spam/Phishing Detection |
Training Models and Measuring Efficacy |
1 |
Intrusion Detection |
Network Intrusion Detection |
1 |
Fraud Detection |
Machine Learning Models for Outlier detection |
1 |
DDoS Detection |
Models with Statistical regression combined with distance metric |
1 |
Total |
|
20 |