Manifold-driven decomposition for adversarial robustness

The adversarial risk of a machine learning model has been widely studied. Most previous studies assume that the data lie in the whole ambient space. We propose to take a new angle and take the manifold assumption into consideration. Assuming data lie in a manifold, we investigate two new types of ad...

תיאור מלא

מידע ביבליוגרפי

Principais autores:	Wenjia Zhang, Yikai Zhang, Xiaoling Hu, Yi Yao, Mayank Goswami, Chao Chen, Dimitris Metaxas
פורמט:	Artigo
שפה:	Inglês
יצא לאור:	Frontiers Media S.A. 2024-01-01
סדרה:	Frontiers in Computer Science
נושאים:	robustness adversarial attack manifold topological analysis of network generalization
גישה מקוונת:	https://www.frontiersin.org/articles/10.3389/fcomp.2023.1274695/full
תגים:	הוספת תג אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!