In recent years, the widespread adoption of Machine Learning (ML) at the core of complex IT systems has driven researchers to investigate the security and reliability of ML techniques. A very specific kind of threats concerns the adversary mechanisms through which an attacker could induce a classification algorithm to provide the desired output. Such strategies, known as Adversarial Machine Learning (AML), have a twofold purpose: to calculate a perturbation to be applied to the classifier’s input such that the outcome is subverted, while maintaining the underlying intent of the original data. Although any manipulation that accomplishes these goals is theoretically acceptable, in real scenarios perturbations must correspond to a set of permissible manipulations of the input, which is rarely considered in the literature. In this article, we present AdverSPAM , an AML technique designed to fool the spam account detection system of an Online Social Network (OSN). The proposed black-box evasion attack is formulated as an optimization problem that computes the adversarial sample while maintaining two important properties of the feature space, namely statistical correlation and semantic dependency . Although being demonstrated in an OSN security scenario, such an approach might be applied in other context where the aim is to perturb data described by mutually related features. Experiments conducted on a public dataset show the effectiveness of AdverSPAM compared to five state-of-the-art competitors, even in the presence of adversarial defense mechanisms.

In recent years, Online Social Networks (OSNs) have radically changed the way people communicate. The most widely used platforms, such as Facebook, Youtube, and Instagram, claim more than one billion monthly active users each. Beyond these, news-oriented micro-blogging services, e.g., Twitter, are daily accessed by more than 120 million users sharing contents from all over the world. Unfortunately, legitimate users of the OSNs are mixed with malicious ones, which are interested in spreading unwanted, misleading, harmful, or discriminatory content. Spam detection in OSNs is generally approached by considering the characteristics of the account under analysis, its connection with the rest of the network, as well as data and metadata representing the content shared. However, obtaining all this information can be computationally expensive, or even unfeasible, on massive networks. Driven by these motivations, in this article we propose SpADe, a multi-stage Spam Account Detection algorithm with reject option, whose purpose is to exploit less costly features at the early stages, while progressively extracting more complex information only for those accounts that are difficult to classify. Experimental evaluation shows the effectiveness of the proposed algorithm compared to single-stage approaches, which are much more complex in terms of features processing and classification time.

In recent years, the widespread diffusion of smart pervasive devices able to provide AI-based services has encouraged research in the definition of new distributed learning paradigms. Federated Learning (FL) is one of the most recent approaches which allows devices to collaborate to train AI-based models, whereas guarantying privacy and lower communication costs. Although different studies on FL have been conducted, a general and modular architecture capable of performing well in different scenarios is still missing. Following this direction, this paper proposes a general FL framework whose validity is assessed by considering a distributed activity recognition scenario in which users' personal devices are employed as the basis of the sensing infrastructure. Experimental analysis was performed to evaluate the effectiveness of the architecture as compared with a centralized approach, under different settings. Results demonstrate the versatility and functionality of the proposed solution.

Assisting users during their cultural trips is paramount in promoting the heritage of a territory. Recommender Systems offer the automatic tools to guide users in their decision process, by maximizing the adherence of the proposed contents with the particular preferences of every single user. However, traditional recommendation paradigms suffer from several drawbacks which are exacerbated in Cultural Heritage scenarios, due to the extremely wide range of users behaviors, which may also depend on their different educational backgrounds. In this paper, we propose a Hybrid recommender system which combines the four most common recommendation paradigms, namely collaborative filtering, popularity-, knowledge-, and content-based, according to different hybridization strategies. Experimental evaluation shows the versatility of the hybrid recommender with respect to the other paradigms adopted individually.

Vehicular Ad-hoc NETworks (VANETs) enable a countless set of next-generation applications thanks to the technological progress of the last decades. These applications rely on the assumption that a simple network of vehicles can be extended with more complex and powerful network infrastructure, in which several Road Side Units (RSUs) are employed to achieve application-specific goals. However, this assumption is not always satisfied as in many real-world scenarios it is unfeasible to have a conspicuous deployment of RSUs, due to both economic and environmental constraints. With the aim to overcome this limitation, in this paper we investigate how the only Vehicle-to-Vehicle (V2V) communications can be effectively exploited to share data among the vehicles about an event of interest, such as vehicular traffic. In this sense, we propose a novel communication schema based on the Population Protocol model that allows vehicles to be efficiently updated about a given event. Experimental analysis aims to evaluate the performance of the proposed schema, while also highlighting the benefits it might bring in VANETs applications.

In recent years, the interest in the study of seas and oceans has dramatically increased as they are considered of primary importance for forecasting catastrophic events or for supporting blue economy, as well as the marine tourism, improving the tourist reception or enhancing any marine-related activity. This led to the development of IT platforms that allow to monitor the marine environment and provide a number of services to different kinds of final users, whether they are private individuals interested in the status of the seas, or companies whose business depends on the marine environmental monitoring. The main limitations of current platforms are due to such a difference between free trials, which often focus only on specific aspects of deep waters, and subscriptions, which provide analyzes whose reliability is generally not proportional to the costs. This paper presents SmartWave, a project funded by Regione Sicilia (European Regional Development Fund), that aims to develop a novel IT platform to observe and predict phenomena that characterize the marine environment, while also providing the consumer with a unified portal to collect, access and analyze marine-related information. To achieve this goal, one of the main challenges of this project is to aggregate and standardize heterogeneous data from multiple sources in order to offer very accurate information to private or business consumers.

Vehicular Social Networks (VSNs) is an emerging communication paradigm, derived by merging the concepts of Online Social Networks (OSNs) and Vehicular Ad-hoc Networks (VANETs). Due to the lack of robust authentication mechanisms, social-based vehicular applications are vulnerable to numerous attacks including the generation of sybil entities in the networks. We address this important issue in vehicular crowdsourcing campaigns where sybils are usually employed to increase their influence and worsen the functioning of the system. In particular, we propose a novel User Recruitment Policy (URP) that, after extracting the participants within the event radius of a crowdsourcing campaign, detects and filters out the sybil vehicles by using a novel sybil detection approach, called SybilDriver. This technique combines the advantages of VANETs and OSNs by means of an innovative concept of proximity graph obtained from the physical vehicular network, in conjunction with a community detection and Random Forest techniques adopted in the OSN domain. Detailed experimental evaluations demonstrate the effectiveness of our approach and also show that it outperforms existing state-of-the-art methods typically used in the OSNs.1

Internet-of-Things (IoT) is a networking architecture where promising, intelligent services are designed via leveraging information from multiple heterogeneous sources of data within the network. However, the availability of such information in a timely manner requires processing and communication of raw data collected from these sources. Therefore, the economic feasibility of IoT-enabled networks relies on the efficient allocation of both computational and communication resources within the network. Since fog computing and 5G cellular networks approach this problem independently, there is a need for joint resource-provisioning of both communication and computational resources in the networks. As the solution to this problem, we propose a novel three-dimensional matching based resource provisioning algorithm that minimizes average service latency in the presence of various resource constraints, task deadlines and non-identical preferences at IoT devices, fog access points (FAPs) and small-cell access points (SAPs) in 5G networks. We prove the stability and termination of the proposed algorithm and also demonstrate that our proposed algorithm outperforms other state-of-the-art algorithms through both, simulation and real-world experiments on the laboratory test-bed.

Online Social Networks (OSNs) have become increasingly popular both because of their ease of use and their availability through almost any smart device. Unfortunately, these characteristics make OSNs also target of users interested in performing malicious activities, such as spreading malware and performing phishing attacks. In this paper we address the problem of spam detection on Twitter providing a novel method to support the creation of large-scale annotated datasets. More specifically, URL inspection and tweet clustering are performed in order to detect some common behaviors of spammers and legitimate users. Finally, the manual annotation effort is further reduced by grouping similar users according to some characteristics. Experimental results show the effectiveness of the proposed approach.

The diffusion of heterogeneous smart devices capable of capturing and analysing data about users, and/or the environment, has encouraged the growth of novel sensing methodologies. One of the most attractive scenarios in which such devices, such as smartphones, tablet computers, or activity trackers, can be exploited to infer relevant information is human activity recognition (HAR). Even though some simple HAR techniques can be directly implemented on mobile devices, in some cases, such as when complex activities need to be analysed timely, users’ smart devices can operate as part of a more complex architecture. In this article, we propose a multi-device HAR framework that exploits the fog computing paradigm to move heavy computation from the sensing layer to intermediate devices and then to the cloud. As compared to traditional cloud-based solutions, this choice allows to overcome processing and storage limitations of wearable devices while also reducing the overall bandwidth consumption. Experimental analysis aims to evaluate the performance of the entire platform in terms of accuracy of the recognition process while also highlighting the benefits it might bring in smart environments.

Technological progress in recent years has allowed the design of new intelligent learning systems in smart environments aiming to facilitate users' lives. As a consequence, besides making use of traditional sensors for monitoring the quantities of interest, such systems can also benefit from information obtained from the users' smart devices, which can now be considered as additional sensing tools. In this article, we present the design of a novel system based on the fog computing paradigm that can improve the services offered to users on a smart campus by using different smart devices, i.e., smartphones, smartwatches, tablets, smartcameras and so on. In particular, we will describe a system in which several smart devices will collect sensory and context information, whilst the cloud will aggregate and analyze this data to extract information of particular interest. The main challenge of this project is to create an intelligent platform that allows new software modules to be added without having to re-design the entire architecture, and that can provide new services to campus users or improve existing ones.

In recent years, the percentage of the population owning a smartphone has increased significantly. These devices provide users with more and more functions that make them real sensing platforms. Exploiting the capabilities offered by smartphones, users can collect data from the surrounding environment and share them with other entities in the network thanks to existing communication infrastructures, i.e., 3G/4G/5G or WiFi. In this work, we present a system based on participatory sensing paradigm using smartphones to collect and share local data in order to monitor make a campus "smart". In particular, our system infers the activities performed by users (e.g., students) in a campus in order to identify trends and behavioral patterns. This information allows the system to decide in real-time which actions are needed to provide the best possible services to users, according to their needs and preferences.