Adversarial machine learning in Network Intrusion Detection Systems

作者：

Highlights：

• Machine learning algorithms are not robust in unconstrained domains.

• Evolutionary algorithms are able to generate successful adversarial examples.

• Generative Adversarial Networks provide a rich source of fooling examples.

• Network intrusion detection systems are vulnerable to maliciously crafted packets.

摘要

•Machine learning algorithms are not robust in unconstrained domains.•Evolutionary algorithms are able to generate successful adversarial examples.•Generative Adversarial Networks provide a rich source of fooling examples.•Network intrusion detection systems are vulnerable to maliciously crafted packets.

论文关键词：Network Intrusion Detection Systems,Adversarial machine learning,Evolutionary computation,Deep learning,Monte Carlo simulation

论文评审过程：Received 14 May 2021, Revised 11 August 2021, Accepted 15 August 2021, Available online 28 August 2021, Version of Record 2 September 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115782