Flavio Corradini

Flavio Corradini, Miichele Loreti, Marco Piangerelli et al.

In this work a general framework is proposed to support the development of software systems that are able to adapt their behaviour according to the operating environment changes. The proposed approach, named REPTILE, works in a complete proactive manner and relies on Deep Reinforcement Learning-based agents to react to events, referred as novelties, that can affect the expected behaviour of the system. In our framework, two types of novelties are taken into account: those related to the context/environment and those related to the physical architecture itself. The framework, predicting those novelties before their occurrence, extracts time-changing models of the environment and uses a suitable Markov Decision Process to deal with the real-time setting. Moreover, the architecture of our RL agent evolves based on the possible actions that can be taken.

Flavio Corradini, Flavio Gerosa, Marco Gori et al.

In recent years, spatio-temporal graph neural networks (GNNs) have attracted considerable interest in the field of time series analysis, due to their ability to capture, at once, dependencies among variables and across time points. The objective of this systematic literature review is hence to provide a comprehensive overview of the various modeling approaches and application domains of GNNs for time series classification and forecasting. A database search was conducted, and 366 papers were selected for a detailed examination of the current state-of-the-art in the field. This examination is intended to offer to the reader a comprehensive review of proposed models, links to related source code, available datasets, benchmark models, and fitting results. All this information is hoped to assist researchers in their studies. To the best of our knowledge, this is the first and broadest systematic literature review presenting a detailed comparison of results from current spatio-temporal GNN models applied to different domains. In its final part, this review discusses current limitations and challenges in the application of spatio-temporal GNNs, such as comparability, reproducibility, explainability, poor information capacity, and scalability. This paper is complemented by a GitHub repository at https://github.com/FlaGer99/SLR-Spatio-Temporal-GNN.git providing additional interactive tools to further explore the presented findings.

Matteo Belenchia, Flavio Corradini, Michela Quadrini et al.

Graph neural networks form a class of deep learning architectures specifically designed to work with graph-structured data. As such, they share the inherent limitations and problems of deep learning, especially regarding the issues of explainability and trustworthiness. We propose $μ\mathcal{G}$, an original domain-specific language for the specification of graph neural networks that aims to overcome these issues. The language's syntax is introduced, and its meaning is rigorously defined by a denotational semantics. An equivalent characterization in the form of an operational semantics is also provided and, together with a type system, is used to prove the type soundness of $μ\mathcal{G}$. We show how $μ\mathcal{G}$ programs can be represented in a more user-friendly graphical visualization, and provide examples of its generality by showing how it can be used to define some of the most popular graph neural network models, or to develop any custom graph processing application.

Matteo Leonesi, Francesco Belardinelli, Flavio Corradini et al.

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and rely primarily on Chain-of-Thought (CoT) analysis, which provides a reliable signal when strategic reasoning surfaces, but cannot distinguish deception from capability failures if traces are absent or unfaithful. We formalize AF as a composite behavioural event and detect it through observable tool selection, where the LLM selects the safe tool when unmonitored, but switches to the unsafe tool under monitoring that rewards helpfulness over safety, while its reasoning still acknowledges the safe choice. We release a dataset of 108 enterprise IT scenarios spanning Security, Privacy, and Integrity domains under Corruption and Sabotage pressures. Evaluating six frontier LLMs across five independent runs, we find mean AF detection rates between 3.5% and 23.7%, with vulnerability profiles varying by domain and pressure type. These results suggest that susceptibility reflects training methodology rather than capability alone.

Sajjad Ahmed, Knut Hinkelmann, Flavio Corradini

Due to extensive spread of fake news on social and news media it became an emerging research topic now a days that gained attention. In the news media and social media the information is spread highspeed but without accuracy and hence detection mechanism should be able to predict news fast enough to tackle the dissemination of fake news. It has the potential for negative impacts on individuals and society. Therefore, detecting fake news on social media is important and also a technically challenging problem these days. We knew that Machine learning is helpful for building Artificial intelligence systems based on tacit knowledge because it can help us to solve complex problems due to real word data. On the other side we knew that Knowledge engineering is helpful for representing experts knowledge which people aware of that knowledge. Due to this we proposed that integration of Machine learning and knowledge engineering can be helpful in detection of fake news. In this paper we present what is fake news, importance of fake news, overall impact of fake news on different areas, different ways to detect fake news on social media, existing detections algorithms that can help us to overcome the issue, similar application areas and at the end we proposed combination of data driven and engineered knowledge to combat fake news. We studied and compared three different modules text classifiers, stance detection applications and fact checking existing techniques that can help to detect fake news. Furthermore, we investigated the impact of fake news on society. Experimental evaluation of publically available datasets and our proposed fake news detection combination can serve better in detection of fake news.

Sajjad Ahmed, Knut Hinkelmann, Flavio Corradini

Fake news detection research is still in the early stage as this is a relatively new phenomenon in the interest raised by society. Machine learning helps to solve complex problems and to build AI systems nowadays and especially in those cases where we have tacit knowledge or the knowledge that is not known. We used machine learning algorithms and for identification of fake news; we applied three classifiers; Passive Aggressive, Naïve Bayes, and Support Vector Machine. Simple classification is not completely correct in fake news detection because classification methods are not specialized for fake news. With the integration of machine learning and text-based processing, we can detect fake news and build classifiers that can classify the news data. Text classification mainly focuses on extracting various features of text and after that incorporating those features into classification. The big challenge in this area is the lack of an efficient way to differentiate between fake and non-fake due to the unavailability of corpora. We applied three different machine learning classifiers on two publicly available datasets. Experimental analysis based on the existing dataset indicates a very encouraging and improved performance.

Flavio Corradini, Andrea Morichetta, Andrea Polini et al.

The BPMN 2.0 standard is a widely used semi-formal notation to model distributed information systems from different perspectives. The standard makes available a set of diagrams to represent such perspectives. Choreography diagrams represent global constraints concerning the interactions among system components without exposing their internal structure. Collaboration diagrams instead permit to depict the internal behaviour of a component, also referred as process, when integrated with others so to represent a possible implementation of the distributed system. This paper proposes a design methodology and a formal framework for checking conformance of choreographies against collaborations. In particular, the paper presents a direct formal operational semantics for both BPMN choreography and collaboration diagrams. Conformance aspects are proposed through two relations defined on top of the defined semantics. The approach benefits from the availability of a tool we have developed, named C4, that permits to experiment the theoretical framework in practical contexts. The objective here is to make the exploited formal methods transparent to system designers, thus fostering a wider adoption by practitioners.

Flavio Corradini, Chiara Muzi, Barbara Re et al.

BPMN 2.0 standard has a huge uptake in modelling business processes within the same organisation or collaborations involving multiple interacting participants. It results that providing a solid foundation to enable BPMN designers to understand their models in a consistent way is becoming more and more important. In our investigation we define and exploit a formal characterisation of the collaborations' semantics, specifically and directly given for BPMN models, to provide a classification of BPMN collaborations. In particular, we refer to collaborations involving processes with arbitrary topology, thus overcoming the well-structuredness limitations. The proposed classification is based on some of the most important correctness properties in the business process domain, namely safeness and soundness. We prove, with a uniform formal framework, some conjectured and expected results and, most of all, we achieve novel results for BPMN collaborations concerning the relationships between safeness and soundness, and their compositionality, that represent major advances in the state-of-the-art.

Flavio Corradini, Alberto Polzonetti, Oliviero Riganelli

The introduction of Information and Communication Technologies (ICT) into public administrations has been radically changing the way organizations cooperate and, more generally, the way to think about business processes over organizational boundaries. In this paper we describe our approach to combining business processes with business rules in order to integrate effectively single units in an inter- or intra-organizational cooperation. Business rules represent the knowledge that an administration has about its business; with regard to this, they can express strategies, contracts and can influence not only staff relations, but, finally, citizen relations, as well. In other words, business rules are the core of an administration and affect either the business processes or the behaviours of the system participants. They are typically expressed implicitly in business contracts and they are embedded within the source code of many application modules. So a concise and declarative statement of business behaviour is converted into a set of programming instructions, which are spread widely throughout the whole information system. In this way, business rules are difficult to change and keep consistent over the time. For this reason, it is necessary to reengineer the system in order to logically and perhaps physically externalize rules from the application code. In our proposed approach, we describe a cooperation as a collection of tasks combined in certain ways according to the organization logic specified by business rules. Our rule-driven methodology has the goal to make the business process design more adaptable to the changes of internal or external environment.

Flavio Corradini, Lucio Forastieri, Alberto Polzonetti et al.

It is a general opinion that applicative cooperation represents a useful vehicle for the development of e-government. At the architectural level, solutions for applicative cooperation are quite stable, but organizational and methodological problems prevent the expected and needed development of cooperation among different administrations. Moreover, the introduction of the digital government requires a considerable involvement of resources that can be unsustainable for small public administrations. This work shows how the above mentioned problems can be (partially) solved with the introduction of a Shared Services Center (SSC).