Provable guarantees that a model's prediction won't change within a specified input perturbation.
A collection of data examples used for training, validating, or testing machine learning models.
The examples a model learns its weights from, kept separate from the validation and test data used to check how well it generalizes.
When a model fits its training data too closely, noise included, so it scores well on examples it has seen and poorly on new ones.
A model's ability to maintain performance under distribution shifts, adversarial attacks, or noisy inputs.
Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.
A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons) organized in layers that process information through weighted connections.
Intentionally crafted inputs designed to fool AI models into making incorrect predictions, exposing vulnerabilities.
An input with imperceptible perturbations that causes a model to make a wrong prediction, highlighting model fragility.
Small carefully crafted changes to input that fool models while imperceptible to humans.
Provable guarantees that a model’s prediction won’t change within a specified input perturbation.
This concept is essential for understanding specialized ai topics and forms a key part of modern AI systems.
Leads to
Nothing yet: a destination in its own right.