Firehose

Filtered to tagged “principal eigenvectors” · clear filters

All PeopleCompaniesPapersPodcastsHacker News

Browse by tag

10 NOV 2026 · Paper

This paper proposes new methods to improve the robustness of machine learning models to adversarial attacks by directly attacking and defending against confidence structure deformation. Practitioners might care because these methods can lead to more reliable models that are less vulnerable to attacks.