A statistical unsupervised method against false data injection attacks: A visualization-based approach

作者：

Highlights：

• An unsupervised method is proposed for detecting cyber-attacks after topology changes.

• Detection is performed by quantifying the probability distributions of the state vectors.

• Quantification is done through extracting several statistical measures.

• Localization of attacks is performed by Fuzzy c-means.

• Performance of classification methods is analyzed in managing system reconfigurations.

摘要

•An unsupervised method is proposed for detecting cyber-attacks after topology changes.•Detection is performed by quantifying the probability distributions of the state vectors.•Quantification is done through extracting several statistical measures.•Localization of attacks is performed by Fuzzy c-means.•Performance of classification methods is analyzed in managing system reconfigurations.

论文关键词：Cyber-attacks,False data injection,Visualization,State estimation,Unsupervised learning,Topology changes,Distributed generation,Smart grid

论文评审过程：Received 10 December 2016, Revised 17 April 2017, Accepted 5 May 2017, Available online 8 May 2017, Version of Record 13 May 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.05.013