Gathering and utilizing stored data is gaining popularity and has become a crucial component of smart building infrastructure. The data collected can be stored, for example, into private, public, or hybrid cloud service infrastructure or distributed service by utilizing data platforms. The stored data can be used when implementing services, such as building automation (BAS). Cloud services, IoT sensors, and data platforms can face several kinds of cybersecurity attack vectors such as adversarial, AI-based, DoS/DDoS, insider attacks. If a perpetrator can penetrate the defenses of a data platform, she can cause significant harm to the system. For example, the perpetrator can disrupt a building's automatic heating system or break the heating equipment by using a suitable attack vector for a data platform. This chapter focuses on examining possibilities to protect cloud storage or data platforms from incoming cyberattacks by using, for instance, artificial-intelligence-based tools or trained neural networks that can detect and prevent typical attack vectors.

No abstract

No abstract

Machine Learning (ML) has been taking significant evolutionary steps and provided sophisticated means in developing novel and smart, up-to-date applications. However, the development has also brought new types of hazards into the daylight that can have even destructive consequences required to be addressed. Evasion attacks are among the most utilized attacks that can be generated in adversarial settings during the system operation. In assumption, ML environment is benign, but in reality, perpetrators may exploit vulnerabilities to conduct these gradient-free or gradient-based malicious adversarial inference attacks towards cyber-physical systems (CPS), such as smart buildings. Evasion attacks provide a utility for perpetrators to modify, for example, a testing dataset of a victim ML-model. In this article, we conduct a literature review concerning evasion attacks and countermeasures and discuss how these attacks can be utilized in order to deceive the, i.e., CPS smart lock system's ML-classifier to gain access to the smart building.