1 code implementation • 21 Dec 2021 • Ziang Li, Yiwen Guo, Haodi Liu, ChangShui Zhang
This paper serves as a complement and somewhat an extension to Guo et al.'s paper, by providing theoretical analyses on LinBP in neural-network-involved learning tasks, including adversarial attack and model training.
no code implementations • 29 Sep 2021 • Li Ziang, Yiwen Guo, Haodi Liu, ChangShui Zhang
In this paper, we study the very recent method called ``linear backpropagation'' (LinBP), which modifies the standard backpropagation and can improve the transferability in black-box adversarial attack.