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.
Logistic regression
How logistic regression works, why it is the most common classifier in security systems, and how red teamers exploit its linear decision boundary in practice.
Linear regression
Linear regression powers SIEM scoring, fraud detection, and baselines. Here is how it works, and why red teamers need to understand it before anything else.
Supervised learning
How supervised learning works, where its assumptions break, and why red teamers need to understand the training pipeline before they can attack it.
The maths behind the models
A working reference for the maths behind AI security tools. Covers linear algebra, probability, and information theory, grounded in real detection use cases.
AI Fundamentals to Red Team AI systems
First in a series on learning to red team AI. Before you break these systems, understand how they learn. AI, machine learning, and deep learning explained.
Brute Force Attacks: Understanding the Threat
Explore brute force attacks, their mechanics, and defense strategies. Learn how to protect your digital assets with strong passwords and security measures.
Monty Hall Paradox: Beat the Odds with Probability Secrets
Unlock the Monty Hall paradox: how switching doors boosts odds to 2/3, explained through game theory, and real-world decision-making strategies.