Re-thinking model robustness from stability: a new insight to defend adversarial examples |
| |
Authors: | Zhang Shufei Huang Kaizhu Xu Zenglin |
| |
Abstract: | Machine Learning - We study the model robustness against adversarial examples, referred to as small perturbed input data that may however fool many state-of-the-art deep learning models. Unlike... |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |