This thesis presents several methodological and statistical solutions to problems encountered in cyber security. We investigated the effects of compromised data veracity in state estimators and fraud detection systems, a model to impute missing data in attributes of linked observations, and an unsupervised approach to detect infected machines in a computer network.
|Qualification||Doctor of Philosophy|
|Award date||7 Jun 2021|
|Place of Publication||Gouda|
|Publication status||Published - 2021|
- Unsupervised learning
- Data veracity