发帖
雷达卡
Globally-Robust Neural Networks
Klas Leino 1 Zifan Wang 1 Matt Fredrikson 1
Abstract
The threat of adversarial examples has motivated
work on training certifiably robust neural networks
to facilitate efficient verification of local robust-
ness at inference time. We formalize a notion of
global robustness, which captures the operational
properties of on-line local robustness certification
while yielding a natural learning objective for
r ...
京公网安备 11010802022788号
