Revision as of 01:42, 15 January 2026

EOT

A method for strengthening adversarial examples to remain adversarial under image transformations that occur in the real world, such as angle and viewpoint changes. EOT models these perturbations within the optimization procedure. Rather than optimizing the log-likelihood of a single example, EOT uses a chosen distribution of transformation functions that take an input controlled by the adversary to the “true” input perceived by the classifier.

Source: NIST AI 100-2e2025 | Category:

Revision as of 00:12, 15 January 2026 view source imported>Unknown user No edit summary	Revision as of 01:42, 15 January 2026 view source imported>Unknown user No edit summary Newer edit →
(No difference)