End-to-end Robustness for Sensing-Reasoning Machine Learning Pipelines

Yang Zhuolin
Yang Zhuolin
Zhao Zhikuan
Zhao Zhikuan
Pei Hengzhi
Pei Hengzhi
Guo Heng
Guo Heng
Cited by: 0|Bibtex|Views33|Links

Abstract:

As machine learning (ML) being applied to many mission-critical scenarios, certifying ML model robustness becomes increasingly important. Many previous works focuses on the robustness of independent ML and ensemble models, and can only certify a very small magnitude of the adversarial perturbation. In this paper, we take a different vie...More

Code:

Data:

Your rating :
0

 

Tags
Comments