activity
20202022
most citedKART: Parameterization of Privacy Leakage Scenarios from Pre-trained Language Models

6 citations · 9 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2020

On the Matrix-Free Generation of Adversarial Perturbations for Black-Box Attacks

Hisaichi Shibata, Shouhei Hanaoka, Yukihiro Nomura +2

In general, adversarial perturbations superimposed on inputs are realistic threats for a deep neural network (DNN). In this paper, we propose a practical generation method of such…