Back close

Course Detail

Course Name Machine Learning for Cybersecurity
Course Code 21SN634
Program M. Tech. in Cyber Security Systems & Networks
Semester Elective
Credits 3


Python, Jupyter Notebooks, Pandas, Numpy, Matplotlib, Seaborn, Scikit-Learn. Mathematics review: derivatives, gradients, sums, products. Supervised learning: Linear regression, Decision Trees, Support Vector Machines, K-nearest neighbors, random forests, adaboost, gradient boosting, multi layer perceptrons, logistic regression. Unsupervised learning: k-means
clustering, dbscan, GMM, PCA, ICA, T-SNE. Bias-variance tradeoff. Learning and validation curves. Cross validation, shuffle split, k-fold, time-series split. Random seeds. Baseline and benchmarking models. Gradient descent, regularization, feature scaling, one hot encoding, label encoding. Train-test-split. Metrics: accuracy, f1-score, precision, recall, confusion matrices. Gini impurity, information gain ration, feature ranking with multivariate and univariate methods. Hyper-parameter tuning with gridsearch and random search, bayesian optimization. Natural language processing, ngrams, bag of words, vectorizers. Pipelines in scikit- learn to avoid overfitting. Data wrangling with feature preprocessing and EDA. Machine learning for security – anomaly detection, fraud detection, malware detection, spam detection, phishing detection, IDS, and NIDS. Security of machine learning: adversarial attacks on machine learning. Data poisoning, model stealing, evasion attacks at inference time. Adversarial hardening.

Text Books and references

  1. Tom M Mitchell, Machine Learning, McGraw Hill, 1997
  2. Jake Vanderplas, Python Data Science Handbook, O’Reilly Media, 2016

Course Outcomes

  • CO1. Learn and understand what Machine learning is, including all the tools of the trade. Understand that linear algebra powers most ML.
  • CO2. Supervised learning, requirement for labeled data, using a loss function to guide the optimization
  • CO3. Learn the fundamentals of regression, using linear regression, decision trees. Difference between continuous outcomes and discrete, including appropriate metrics
  • CO4. Fundamentals of classification, decision trees, logistic regression, SVM’s. Neural networks. Appropriate metrics
  • CO5. Model validation and evaluation. Gain the skill of plotting both learning curves and model evaluation curves. Ascertain whether more complexity is required or more data.
  • CO6. Dimensionality reduction and clustering. Understanding PCA, and k-means clustering.
  • CO7. Learn to conduct anomaly detection, spam classification, automated malware classification. Security oriented machine learning tasks.
  • CO8. Threat modeling for machine learning, understanding adversarial attacks on vision and text. Commonly known defenses, dangers of

DISCLAIMER: The appearance of external links on this web site does not constitute endorsement by the School of Biotechnology/Amrita Vishwa Vidyapeetham or the information, products or services contained therein. For other than authorized activities, the Amrita Vishwa Vidyapeetham does not exercise any editorial control over the information you may find at these locations. These links are provided consistent with the stated purpose of this web site.

Admissions Apply Now