|Daniele Codetta Raiteri
|Probabilistic Graphical Models
|Dependability and Reliability
|A modular infrastructure for the validation of cyberattack detection systems
|DiSIT, Computer Science Institute, UPO
|We propose a framework for the evaluation of cyberattack detection systems in which methodological results can be tested in a realistic setup. We emulate a power control infrastructure, an attacker and a monitoring systems. In this controlled environment, through a modular approach, we can evaluate a variety of detection models: we inject adversarial activity, collect logs from the systems, analyze such logs and produce evidences that are later processed by artificial intelligence models that can raise alerts, and give diagnostic or predictive information. The testbed allows us to effectively test the adequacy of the detection mechanisms; currently, it includes man-in-the-middle attacks and false data injection.