Picuslab

We are pleased to share that Professor Carlo Sansone participated in Feuromed, the Euro-Mediterranean Festival of Economy, organized by L'AltraVoce - Il Quotidiano. This event serves as a key platform for discussions on economic, technological, and social issues affecting the Euro-Mediterranean region. The main theme was a "Mediterranean model for Artificial Intelligence", in the year when this technology enters as a protagonist in geopolitics and major development strategies, but also in industrial processes of territory, public services and citizens' relational life. During the festival, professor Sansone took part in the roundtable "Services/AI as a bridge between citizens and the State in defense of democracy", alongside Giorgio Ventre, Scientific Director of the Apple Developer Academy, and Maurizio Lenzerini, Professor at La Sapienza - University of Rome. The discussion, moderated by Sergio Bellucci, explored the role of artificial intelligence in strengthening the relationship between citizens and institutions, contributing to the protection of democracy.

EmTech Italy 2025 took place in Rome, bringing together visionary leaders to explore the transformative impact of AI across industries. Organized by MIT Technology Review Italia, the two-day conference focused on the interconnection of health, energy, and environmental sectors, providing a platform for discussions on emerging trends and the role of AI in addressing global and social challenges. As part of the event, Prof. Carlo Sansone, as Director of the Italian National Laboratory on Artificial Intelligence and Intelligent Systems (LN AIIS) - CINI, joined the roundtable "Decoding AI: Understanding the Mechanics of Large AI Models and Their Transformative Impact". Alongside Marco Conti, President of the FAIR Foundation, and moderated by Paolo Soda, Coordinator of the National PhD Program in AI for Health and Life Sciences, the discussion explored the architecture, functionality, and social implications of large AI models, emphasizing their growing influence on innovation and society. The panel also explored the work of the Future AI Research - FAIR Foundation and the importance of developing reliable AI models. This event provided a great platform for exchanging ideas, discussing emerging trends, and identifying AI as a key driver of transformation to tackle global challenges. #AI #EmTechItaly2025 #MIT #FAIR

Professor Carlo Sansone participated in the conference "Artificial Intelligence: from Processing to Generation", held on Monday, March 10, at the Darwin Dohrn Museum of the Anton Dohrn Zoological Station. The event was organized in collaboration with the Academy of Fine Arts of Naples. Professor Sansone contributed with a talk titled "An Introduction to Generative AI", providing insights into the potential and implications of Artificial Intelligence in different domains. This conference was an important opportunity for discussion between industry experts and students interested in the new frontiers of AI. Thank you to all participants for making this event a valuable moment of dialogue and knowledge sharing!

📣 Today marked the end of the second Future AI Research - FAIR Workshop on Resilient AI, organised by Spoke 3 "Resilient AI" at the Università degli Studi di Napoli Federico II. The event concluded with a round table discussion moderated by Prof. Carlo Sansone, Vice President of the FAIR Foundation, and Prof. Sergio Di Martino, Head of Spoke 3. The session featured presentations from companies that have received cascade funding totalling over €1.5 million, highlighting the strong link between academic research and industrial applications. 🦾 A big thank you to all the participants over the two days, to prof. giuseppe de pietro, President of the FAIR Foundation, and a special thanks to the PicusLab members whose contributions helped to make this event a success!

Today marked the first day of the Second FAIR Workshop on Resilient AI, organized by Spoke 3 "Resilient AI" as part of the FAIR - Future AI Research project. 🔍 Key research findings from the multidisciplinary team involved in Spoke 3 were presented, with a focus on innovative approaches for training AI models with real-world data and their legal and social implication. ⭐We extend our gratitude to the PicusLab members for their valuable contributions, as well as to prof. Carlo Sansone, Vice-President of the FAIR Foundation, and prof. Sergio Di Martino, Head of Spoke 3, for their active roles in the workshop. The workshop will continue tomorrow, March 7, with a roundtable moderated by prof. Sansone, featuring representatives from companies that have won cascade funding grants for industrial research. 🔗 More details here: https://lnkd.in/dtwTC97F .

Picuslab is happy to share their last publication entitled “Design of a Machine Learning Approach to Anomaly Detection in Tyre-Road Interaction” – whose authors are Aleksandr Sakhnevych, Nicola Pasquino, and Giancarlo Sperlì – has been accepted in the IEEE Access journal. In this paper, the authors aim to optimize the process of identifying tyre parameters through two phases: first, different clustering algorithms are applied to the tyre data to group similar operating conditions; then, anomaly detection algorithms are applied to clustered data to recognize and remove inconsistencies. https://lnkd.in/dfdSjakp #artificialintelligence #anomalydetection #tyreroadinteraction

Picuslab is thrilled to share their last publication entitled “Empowered Cyber-Physical Systems security using both network and physical data” – whose authors are Roberto Canonico, Giovanni Esposito, Annalisa Navarro, Simon Pietro Romano, Giancarlo Sperlì and Andrea Vignali – has been accepted in Elsevier Computers & Security journal. In this paper, we propose a novel two-stage framework for threat detection in CPSs. This framework integrates anomaly detection models that operate on both network and physical data, by leveraging a decision fusion technique to combine the outputs into a coherent decision. To assess the effectiveness of the framework, we employ an unlabeled release of a real-world dataset, integrating network traffic with sensors/actuators data. Additionally, we offer explicit labeling rules to ensure reproducibility. https://lnkd.in/dSYkt5BT #multimodalanalysis #anomalydetection #threatdetection #artificialintelligence

Picuslab is thrilled to share their last publication entitled “An anomaly-based approach for cyber–physical threat detection using network and sensor data” – whose authors are Roberto Canonico, Giovanni Esposito, Annalisa Navarro, Simon Pietro Romano, Giancarlo Sperlì and Andrea Vignali – has been accepted in Elsevier Computer Communications journal. In this study, we meticulously design advanced Deep Learning (DL) anomaly-based techniques trained on either sensor/actuator data or network traffic statistics in an unsupervised setting. We evaluate these techniques on network and physical data collected concurrently from a real-world CPS. https://lnkd.in/dhzCh3Se #threatdetection #anomalydetection #artificialintelligence #cps

📣 PicusLab is pleased to share our latest publication, "Can Generative Agent-Based Modeling Replicate the Friendship Paradox in Social Media Simulations?". This work, authored by Gian Marco Orlando, Valerio La Gatta, Diego Russo and Vincenzo Moscato, explores how Generative Agent-Based Modeling (GABM) can be used to replicate the Friendship Paradox in social media simulations. Using real Twitter data, focusing on the 2020 US Election and the QAnon conspiracy, the paper demonstrates how GABM can simulate global social network dynamics, where, on average, individuals have fewer friends than their friends have. The results reveal that the Friendship Paradox naturally emerges from the simulations, with a hierarchical structure where agents tend to connect with more active or influential users. Additionally, infrequent connections are found to primarily drive the phenomenon, reflecting patterns observed in real-world networks. 🔬 Read the full paper here: https://lnkd.in/dwzq_D_Y

📢 Professor Carlo Sansone participated as invited speaker at the event "Lionism 5.0 – Artificial Intelligence: Opportunities and Risks", organized by the Lions Clubs International in Naples, held at the Teatro Auditorium Salesiano Salvo D’Acquisto. This event focused on the role of Artificial Intelligence across various fields, from medical applications to robotics, as well as ethical and regulatory implications. Prof. Sansone contributed to a high-level multidisciplinary discussion alongside other experts in the field from Università degli Studi di Napoli Federico II, also presenting the activities of Future AI Research (FAIR). Thank you to the Lions Club for this initiative, and also to all the other speakers who contributed to the event!