Adversarial Examples

Generating Less Certain Adversarial Examples Improves Robust Generalization
Build upon the notion of adversarial certainty, we develop a general training method to generate adversarial examples with reduced certainty for improving robust generalization.
PDF Cite Code ArXiv OpenReview
Understanding Adversarially Robust Generalization via Weight-Curvature Index
We introduce the Weight-Curvature Index (WCI), a novel metric that captures the interplay between model parameters and loss landscape curvature to better understand and improve adversarially robust generalization in deep learning.
PDF Cite ArXiv OpenReview