46 citations · 173 across the 13 of their papers we have counts for
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2023
EMShepherd: Detecting Adversarial Samples via Side-channel Leakage
Ruyi Ding, Cheng Gongye, Siyue Wang +2
Deep Neural Networks (DNN) are vulnerable to adversarial perturbations-small changes crafted deliberately on the input to mislead the model for wrong predictions. Adversarial attac…
cs.CR2018★ 45 cited
Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attacks
Siyue Wang, Xiao Wang, Pu Zhao +4
Deep neural networks (DNNs) are known vulnerable to adversarial attacks. That is, adversarial examples, obtained by adding delicately crafted distortions onto original legal inputs…