AI-based anomaly detection for smart homes - data generation and ML-based anomaly detection within the smart home network
Due to the ongoing digitization and networking of originally analog measurement and control components in smart homes, targeted attempts at manipulation and malfunctions in these are increasing. Ransomware accessing and encrypting sensitive files can cause financial and personal damage. KIASH enables integrators, installers, electrical engineers and craft businesses to offer their customers security monitoring for smart homes and thus to establish new value-added processes, including simple digital procurement, without having to have expertise in the AI or security area themselves. To date, companies have lacked resources such as budgets, personnel and know-how. The KIASH project starts here by developing the KIASH Security Box with the help of SMEs and scientific partners, which finds its way into application with intensive involvement of corresponding companies.
The sub-project of Worms University of Applied Sciences in the KIASH project essentially consists of test data generation and research work in the field of machine learning/heuristic-based anomaly detection on heterogeneous IoT data.