Invited Talk
in
Workshop: 2nd Workshop on Formal Verification of Machine Learning

Prof. Aws Albarghouthi and Yuhao Zhang (UW-Madison): Certifying Robustness: From Training to Inference

Aws Albarghouthi ⋅ Yuhao Zhang

2023 Invited Talk
in
Workshop: 2nd Workshop on Formal Verification of Machine Learning

Abstract

Researchers have demonstrated that the machine-learning pipeline is susceptible to attacks both at training and inference time -- poisoning, backdoor, and evasion attacks. In this talk, we will describe new results on holistic approaches for certifying robustness. Our techniques draw upon ideas from test-time certification and ensembling to simultaneously establish formal robustness guarantees for both training and inference.

Speakers

Yuhao Zhang

First-year PhD student at madPL, UW-Madison

Aws Albarghouthi

Video

Chat is not available.