Modern cars include a huge number of sensors and actuators, which continuously exchange data and control commands. The most used protocol for communication of different components in automotive system is the Controller Area Network (CAN). According to CAN, components communicate by broadcasting messages on a bus. In addition, the standard definition of the protocol does not provide information for authentication, so exposing it to attacks. This paper proposes a method based on deep learning aiming at discovering attacks towards the CAN-bus. In particular, Neural Networks and MultiLayer Perceptrons are the class of networks employed in our approach. We also validate our approach by analysing a real-world dataset with the injection of messages from different types of attacks: denial of service, fuzzy pattern attacks, and attacks against specific components. The obtained results are encouraging and demonstrate the effectiveness of the approach.

Viral marketing is the modern version of the old “word-of-mouth” advertising, where companies choose a restricted number of persons, considered “influential,” recommending them products or services that will be in turn iteratively suggested. In this article, we propose cognitive models and algorithms for marketing applications through online social networks, considered as a graph database, and define the concept of influence graph leveraging particular user behavioral patterns, by querying the initial heterogeneous graph network. We also model the diffusion across the network, without any preliminary information, as a combinatorial multiarmed bandit problem, for the selection of most influential users. We have used the YELP social network as a case study for our approach, showing how it is possible to generate an influence graph considering several kinds of relevant paths (mainly considering reviews to the same firms) by which a user can influence other ones. Several experiments have been carried out and discussed, putting into evidence the effectiveness and efficacy of the proposed methods for influence maximization with respect to other approaches of state of the art.

Internet of Things (IoT) ecosystems are recently experiencing a significant grow in complexity. Most IoT applications in domains like healthcare, industry, automotive and smart energy are composed of several interconnected sub-systems that produce, collect, process and exchange a huge amount of data, and that offer composite services to the end-users based on this data. This scenario is exacerbated by the dynamism of the IoT device layer, which may subject to structural or technological changes over time, to cope for example with the need of new sensing/actuation capabilities requirements or with technical issues. Due to the inherent sensitive nature of the data that is typically processed by IoT applications, security represents one of the primary issues to address. It is worth noting that each sub-system integrated within a composite IoT application may have different requirements and enforce different local security policies, and the policies that result globally enforced at the system level may not comply with existing global requirements. In general, the analysis and validation of security properties in a composite IoT system represents a very complex task, made even more complex by the introduction of new laws and regulations during system life. To cope with the above issues, in this paper we propose a methodology that leverages both workflow languages and semantics in order to enable the validation of the security features offered by a composite IoT system, with the goal of verifying whether they match with global end-user policies and even with national and international laws and rules.

The increasing complexity of services required by users in Cloud Environments usually needs the definition of composite, value added services (VAS). Usage patterns and Use Cases definitions help in defining VAS, but a way to assure that new services reach the required goals with proper qualitative and quantitative properties has to be provided in order to validate design and implementation of composite services. In this paper the MetaMORP(h)OSY methodology and framework are introduced. The methodology uses Model Driven Engineering and Model Transformation techniques to analyze composite services. Due to the complexity of the systems to analyze, MetaMORP(h)OSY exploits Multi Agent System (MAS) in system definition. The methodology is used in order to define a model for a Use Case of the mosaic project.