Training and evaluating your first spam classifier
Build, tune, and evaluate a Naive Bayes spam classifier with scikit-learn, then examine what the model reveals to an adversary in this AI red teaming entry.
Feature extraction
How extraction builds the feature space a spam classifier learns from, and why every vocabulary decision creates an evasion path for a red teamer to find.
Preprocessing the spam dataset
Every text cleaning step in a spam classifier either blocks an evasion path or opens one. See how preprocessing shapes what the model can and cannot see.
Bayesian spam classification: the dataset
Preparing the SMS Spam Collection dataset for Bayesian classification, covering download, extraction, loading, and cleaning through an adversarial lens.
Spam classification: Naive Bayes filters
How Naive Bayes spam filters work, why the independence assumption makes them exploitable, and how GoodWords attacks broke email filtering wide open.
Metrics for evaluating a model
Learn how accuracy, precision, recall, and F1-score work in practice, where each metrics deceive, and how adversaries exploit the gaps they leave behind.
Data preprocessing
How cleaning, validation, and imputation decisions in data preprocessing pipelines create exploitable assumptions in models.
Datasets and data quality
Entry 14 in the AI red teaming series. How datasets structure, quality assumptions, and preprocessing pipelines create attack surfaces for data poisoning.
Python libraries for AI red teaming
Python Libraries: How scikit-learn and PyTorch work, and why their APIs are the operational foundation for adversarial machine learning.
Getting started with JupyterLab
Get started with JupyterLab: interactive notebooks for data analysis. Create, visualise, and document your Python work.