Computer Science - Machine Learning

What it Thinks is Important is Important: Robustness Transfers through Input Gradients
TL;DR: By regularizing for similar input gradients, we can transfer adversarial robustness from a teacher to a student classifier even …
<strong>Alvin Chan</strong>*, Yi Tay, Yew-Soon Ong
PDF Cite Code Video
Poison as a Cure: Detecting & Neutralizing Variable-Sized Backdoor Attacks in Deep Neural Networks
TL;DR: We propose a comprehensive defense to detect and neutralize backdoor poisoning attacks of different sizes.
Abstract: Deep …
<strong>Alvin Chan</strong>*, Yew-Soon Ong
PDF Cite