Software Updates Monitoring & Anomaly Detection

Security is becoming a must in the current all-connected paradigm. Software updates are essential to fix
any new identified security flaw or vulnerability that may appear as they normally are the fastest and cheapest
solution. Nevertheless, a software update targeted to fix a determined issue could end up in a different problem.
In order to detect these new issues, systems should be able to gather monitoring data so that possible effects
and consequences are observed and characterized. This is specially relevant when upgrades are performed
remotely, like in road vehicles, and no prior outcome information is available to the manufacturer. In this
paper, a software updates monitoring, an anomaly detection procedure and a proof-of-concept are presented.
The monitoring and anomaly detection approach enable the detection of performance anomalies that could
result for instance, from malicious code installation during an update. This offline monitoring information can
also be used for further system design improvements and to facilitate the review and assessing processes of
security issues.