ML for Cyber Security
Sign in to save your progress, earn points, and unlock module exams.
MLCS
Machine learning applied to security problems: malware classification, anomaly and intrusion detection, phishing and spam detection, adversarial robustness, and the practical pipeline from raw security data to a deployed model.
Instructor: Ashish Revar
Unit 1
Why a security analyst benefits from thinking statistically, where ML already runs in production security tools, the four threat families, the Cyber Kill Chain, a short history of learning-based defence, a worked blacklist-versus-classifier example, and the five-stage ML pipeline every later unit reuses.
Unit 2
Decision trees, random forests, support vector machines and gradient boosting applied to labelled security data, hyperparameter tuning, cross-validation, voting ensembles, and a production-scale credit card fraud case study.
No sign-in required, read these right now
An attacker must succeed at every stage of the kill chain in order. A defender only has to break it once, and a trained model is often the cheapest way to break a specific link.
Read article ml for cyber securityNearly every threat a security team meets falls into one of four families, and each one favours a different kind of model. That mapping is why this course is organised the way it is.
Read articleCreate a free account to track your progress, take assessments, and earn a verifiable certificate.