Reference 3 stops to get here · leads to 2

Adversarial Example

An input with imperceptible perturbations that causes a model to make a wrong prediction, highlighting model fragility.

Your route here

3 stops · basics first
  1. Machine Learning ✓ understood

    Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.

  2. Neural Network ✓ understood

    A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons) organized in layers that process information through weighted connections.

  3. Adversarial Attack ✓ understood

    Intentionally crafted inputs designed to fool AI models into making incorrect predictions, exposing vulnerabilities.

  4. Adversarial Example · you are here ✓ understood

Where it sits

Before this

Adversarial Attack
Adversarial Example

Leads to

Adversarial Perturbation Adversarial Training

Explore nearby

Shipping AI Adversarial Perturbation Small carefully crafted changes to input that fool models while imperceptible to humans. Shipping AI Adversarial Training Training on adversarial examples to improve model robustness against attacks. Evaluation Robustness A model's ability to maintain performance under distribution shifts, adversarial attacks, or noisy inputs. Shipping AI Certified Robustness Provable guarantees that a model's prediction won't change within a specified input perturbation.