Cardio-ML: Detection of malicious clinical programmings aimed at cardiac implantable electronic devices based on machine learning and a missing values resemblance framework

作者：

Highlights：

• An ML-based mechanism was proposed to protect ICD patients from cyber attacks.

• The mechanism learns clinical cardiac programmings created during patients' visits.

• The mechanism is automated and thus reduces the need for human-experts' knowledge.

• Our mechanism improves the detection of new malicious clinical programmings.

• A new generic and automated framework to cope with missing values was proposed too.

摘要

•An ML-based mechanism was proposed to protect ICD patients from cyber attacks.•The mechanism learns clinical cardiac programmings created during patients' visits.•The mechanism is automated and thus reduces the need for human-experts' knowledge.•Our mechanism improves the detection of new malicious clinical programmings.•A new generic and automated framework to cope with missing values was proposed too.

论文关键词：ICD,CIED,Cyber-attack,Machine learning,Missing values,Malware,Detection

论文评审过程：Received 9 March 2021, Revised 18 October 2021, Accepted 22 October 2021, Available online 27 October 2021, Version of Record 13 November 2021.

论文官网地址：https://doi.org/10.1016/j.artmed.2021.102200