A Geometric Perspective on the Transferability of Adversarial Directions

• Main Authors: Charles, Zachary, Rosenberg, Harrison, Papailiopoulos, Dimitris
• Format: Journal Article
• Language: English
• Published: 08.11.2018
• Subjects: Computer Science - Learning; Statistics - Machine Learning

State-of-the-art machine learning models frequently misclassify inputs that have been perturbed in an adversarial manner. Adversarial perturbations generated for a given input and a specific classifier often seem to be effective on other inputs and even different classifiers. In other words, adversa...