Applied Data Science and Machine Learning for Cyber Security
This advanced course in Toronto teaches machine learning as it is actually applied to security problems, not as a general data science class with security examples bolted on. You will build anomaly detection, classification, and malware clustering on real security telemetry.
The hardest part of security machine learning is honest evaluation. Attacks are rare, so the data is extremely imbalanced, and a model that looks accurate can be useless. Confronting that is the core of the course.
- Duration
- 10 weeks
- Format
- Live online, instructor-led
- Prerequisites
- None required
- Class size
- Capped at 12 learners
What you will be able to do
- Frame a security problem as a machine learning task, or decline to
- Engineer features from logs, network, and endpoint telemetry
- Build anomaly detection suited to rare events
- Train classifiers for tasks such as malware or phishing detection
- Cluster malware or events to surface structure
- Evaluate models honestly under extreme class imbalance
- Explain a model's limits to a security team that will rely on it
Course outline
6 modules
- When machine learning fits a security problem
- Supervised, unsupervised, and where each applies
- The base rate problem in security data
- Setting up a reproducible workflow
What you need before you start
- You can program in Python and have used a data analysis library
- You understand basic statistics such as distributions and rates
- You work in or understand security data and operations
- You are prepared to accept when a model is not good enough to ship
Who this course is for
- Security engineers building or assessing ML-based tooling
- Data scientists moving into the security domain
- Detection engineers who want to go beyond static rules
- Analysts curious about the models behind their tools
Questions about this course
More in ai security
CoreAI Security Principles and Practices: GenAI and LLM Defence
The foundational AI security course: threat model generative AI, defend against prompt injection, and set pragmatic policy for an enterprise rolling out AI.
8 weeks · live online
Contact for pricingView outline
CoreBuilding and Securing RAG and Agentic AI Systems
Build retrieval augmented generation and agentic AI hands on, then secure them: indirect injection, vector store isolation, and constrained agent tools.
8 weeks · live online
Contact for pricingView outline
CoreAdversarial AI: Penetration Testing AI Systems
Penetration test AI systems themselves: model attacks, jailbreak methodology, data extraction, and reporting findings that are probabilistic, not binary.
6 weeks · live online
Contact for pricingView outline
Ready to launch your cyber security career?
Join the next live online cohort. No experience required, just bring the curiosity.