Cyber-threat protection is today's one of the most challenging research branches of information technology, while the exponentially increasing number of tiny, connected devices able to push personal data to the Internet is doing nothing but exacerbating the battle between the involved parties. Thus, this protection becomes crucial with a typical Internet-of-Things (IoT) setup, as it usually involves several IoT-based data sources interacting with the physical world within various application domains, such as agriculture, health care, home automation, critical industrial processes, etc. Unfortunately, contemporary IoT devices often offer very limited security features, laying themselves open to always new and more sophisticated attacks and also inhibiting the expected global adoption of IoT technologies, not to mention millions of IoT devices already deployed without any hardware security support. In this context, it is crucial to develop tools able to detect such cyber threats. In this article, we present Passban, an intelligent intrusion detection system (IDS) able to protect the IoT devices that are directly connected to it. The peculiarity of the proposed solution is that it can be deployed directly on very cheap IoT gateways (e.g., single-board PCs currently costing few tens of U.S. dollars), hence taking full advantage of the edge computing paradigm to detect cyber threats as close as possible to the corresponding data sources. We will demonstrate that Passban is able to detect various types of malicious traffic, including Port Scanning, HTTP and SSH Brute Force, and SYN Flood attacks with very low false positive rates and satisfactory accuracies.

According to the World Health Organization, the rate of people aged 60 or more is growing faster than any other age group in almost every country, and this trend is not going to change in a near future. Since senior citizens are at high risk of non communicable diseases requiring long-term care, this trend will challenge the sustainability of the entire health system. Pervasive computing can provide innovative methods and tools for early detecting the onset of health issues. In this paper we propose a novel method relying on medical models, provided by cognitive neuroscience researchers, describing abnormal activity routines that may indicate the onset of early symptoms of mild cognitive impairment. A non-intrusive sensor-based infrastructure acquires low-level data about the interaction of the individual with home appliances and furniture, as well as data from environmental sensors. Based on those data, a novel hybrid statistical-symbolical technique is used to detect first the activities being performed and then the abnormal aspects in carrying out those activities, which are communicated to the medical center. Differently from related works, our method can detect abnormal behaviors at a fine-grained level, thus providing an important tool to support the medical diagnosis. In order to evaluate our method we have developed a prototype of the system and acquired a large dataset of abnormal behaviors carried out in an instrumented smart home. Experimental results show that our technique has a high precision while generating a small number of false positives.