Adversarial Learning: A Critical Review and Active Learning Study

David J. Miller; Xinyi Hu; Zhicong Qiu; George Kesidis

Adversarial Learning: A Critical Review and Active Learning Study

Cryptography and Security 2017-05-30 v1

Authors: David J. Miller , Xinyi Hu , Zhicong Qiu , George Kesidis

Abstract

This papers consists of two parts. The first is a critical review of prior art on adversarial learning, identifying some significant limitations of previous works. The second part is an experimental study considering adversarial active learning and an investigation of the efficacy of a mixed sample selection strategy for combating an adversary who attempts to disrupt the classifier learning.

Keywords

adversarial examples machine learning

Cite

@article{arxiv.1705.09823,
  title  = {Adversarial Learning: A Critical Review and Active Learning Study},
  author = {David J. Miller and Xinyi Hu and Zhicong Qiu and George Kesidis},
  journal= {arXiv preprint arXiv:1705.09823},
  year   = {2017}
}

Related papers

View all related →