Evasion attack
Class A (benign) Class B (malicious) Attack target Poisoned point
⚠ Couldn't load the 3D engineThree.js failed to load from the CDN. Check your connection and reload.

Adversarial ML Attacks: Evasion & Poisoning

A minimal nearest-centroid classifier splits a 3D feature space into two classes with a flat decision boundary. Switch between an evasion attack, which perturbs a single input vector until it crosses the boundary, and a data-poisoning attack, which injects mislabeled training points that pull the boundary itself out of place.