Impact of benign sample size on binary classification accuracy

作者：

Highlights：

• We propose a metric for accuracy degradation by increasing benign samples.

• Increasing the test benign sample size tenfold decreased the F1 score by 0.293.

• Using sufficient benign training samples mitigates accuracy degradation.

摘要

•We propose a metric for accuracy degradation by increasing benign samples.•Increasing the test benign sample size tenfold decreased the F1 score by 0.293.•Using sufficient benign training samples mitigates accuracy degradation.

论文关键词：Malware,Machine learning,Binary classification,Benign sample,Random forest,Support vector machine,XGBoost

论文评审过程：Received 25 November 2021, Revised 22 June 2022, Accepted 17 August 2022, Available online 27 August 2022, Version of Record 2 September 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118630