Term tag: robustness

AI Safety

AI safety is three fields, not one: present-day reliability, alignment, and catastrophic risk. What each actually claims, and why they get confused.

Concept Drift

Concept drift is when the relationship a deployed model learned changes over time, so accuracy silently decays until you detect the drift and retrain.

Data Augmentation

Making new training examples by transforming existing ones. Valid only when the label is indifferent to the transform — and it adds variety, not information.

Data Poisoning

Data poisoning is a cyberattack where malicious actors insert corrupted or misleading data into an AI model's training set to manipulate its future.

Jailbreak (Red-Teaming)

A jailbreak is an input that steers an AI past its safety training to produce content it was built to refuse. How they work, and how they are defended.

Robustness

A model's ability to keep performing when inputs are noisy, out of distribution, or crafted by an attacker — not just accurate on clean test data.