\n\n\n\n
![\"\"](\"https:\/\/sites.unica.it\/pralab\/files\/2024\/03\/TrustML_project_logo.png\"){kind=logo}
<\/a><\/figure>TrustML – Towards Machine Learning that Humans can Trust<\/strong><\/a> <\/strong>(September 2022 \u2013 October 2024)<\/p>\n\n\n\n Machine learning (ML) and Artificial intelligence (AI) have recorded unprecedented success in different applications, including computer vision, speech recognition, and natural language processing. Despite providing accurate predictions, such models suffer from several limitations which prevent their applicability in security-sensitive and safety-critical domains. In this project, we aim to address three main challenges that are hindering the development of trustworthy AI\/ML models in these domains.<\/p>\n\n\n\n People involved<\/strong>: Battista Biggio<\/strong><\/a>, Giorgio Giacinto<\/a>, Giorgio Fumera<\/a>, Luca Didaci<\/a>, Matteo Fraschini<\/p>\n\n\n\n Budget<\/strong>: 52777.78 \u20ac<\/p>\n<\/div><\/div>\n\n\n\n BullyBuster 2 \u2013 the ongoing fight against bullying and cyberbullying with the help of artificial intelligence for the <\/a>human <\/a>wellbeing<\/a> (November 2023 – November 2025)<\/p>\n\n\n\n Supported by the European Union \u2013 Next Generation EU and within the PRIN 2022 PNRR. The BullyBuster2 project combines artificial intelligence, technology, law, and psychology expertise to develop a comprehensive framework for detecting and addressing bullying and cyberbullying.<\/p>\n\n\n\n People involved: Gian Luca Marcialis<\/strong><\/a>, Giulia Orr\u00f9<\/a>, Giovanni Puglisi, Marco Micheletto<\/a>, Sara Concas<\/a>, Simone Maurizio La Cava<\/a>, Gianpaolo Perelli<\/a>, Andrea Panzino<\/a><\/p>\n\n\n\n Partners: University of Bari Aldo Moro<\/a>, University of Foggia<\/a>, University of Naples Federico II<\/a><\/p>\n\n\n\n Budget: 299.258,00 \u20ac<\/p>\n<\/div><\/div>\n\n\n\n Sec4AI4Sec – Cybersecurity for AI-Augmented Systems<\/strong><\/a><\/strong> (October 2023 – September 2026)<\/p>\n\n\n\n Funded by the European Union under the HORIZON EUROPE programme (grant agreement n. 101120393). Sec4AI4Sec aims to create a range of cutting-edge technologies, open-source tools, and new methodologies for designing and certifying secure AI-enhanced systems and AI-enhanced systems for security. Furthermore, it will establish a set of reference benchmarks to standardize research outcomes in the secure software research community.<\/p>\n\n\n\n People involved<\/strong>: Battista Biggio<\/strong><\/a>, Maura Pintor,<\/a> Ambra Demontis<\/a>, Giorgio Piras<\/a>, Matteo Mauri<\/p>\n\n\n\n Partners<\/strong>: University of Trento, SAP S.E., Airbus Operations, FrontEndART, Cefriel, Vrije Universiteit Amsterdam, Pluribus One, Oppida, Technische Universit\u00e4t Hamburg, Thales, Universit\u00e0 della Svizzera Italiana<\/p>\n\n\n\n Budget<\/strong>: 4283037,50 \u20ac<\/p>\n<\/div><\/div>\n\n\n\n ELSA – European Lighthouse on Secure and Safe AI<\/a><\/strong> (September 2022 – August 2025)<\/p>\n\n\n\n Funded by the European Union under the HORIZON EUROPE programme (grant agreement n. 101070617). In order to reinforce European leadership in safe and secure AI technology, ELSA proposes a virtual center of excellence on safe and secure AI that will address major challenges hampering the deployment of AI technology.<\/p>\n\n\n\n People involved<\/strong>: Battista Biggio<\/strong><\/a>, Maura Pintor,<\/a> Ambra Demontis<\/a>, Angelo Sotgiu<\/a>, Matteo Mauri<\/p>\n\n\n\n Partners<\/strong>: CISPA Helmholtz Center for Information Security, University of Helsinki, KTH Royal Institute of Technology, Computer Vision Center (CVC-CERCA), Italian Institute of Technology (IIT), Valeo, University of Modena and Reggio Emilia, National Interuniversity Consortium for Informatics (CINI), University of Genoa, University of Milano, Polytechnic University of Turin, Max Planck Society, National Institute for Research in Computer Science and Automation, European Molecular Biology Laboratory, Pluribus One, Yooz, Leonardo, PAL Robotics, EPFL, ETH Zurich, NVIDIA, The University of Oxford, Lancaster University, University of Birmingham, Alan Turing Institute.<\/p>\n\n\n\n Budget<\/strong>: 7434058,75 \u20ac<\/p>\n<\/div><\/div>\n\n\n\n S3AI – Security and Safety for Shared Artificial Intelligence by Deep Model Design<\/a> <\/strong>(January 2020 – December 2024)<\/p>\n\n\n\n S3AI is a COMET Module within the COMET \u2013 Competence Centers for Excellent Technologies Programme and funded by BMK, BMDW and the government of Upper Austria. The COMET Programme is managed by FFG. People involved<\/strong>: Battista Biggio<\/strong><\/a>, Maura Pintor,<\/a> Ambra Demontis<\/a><\/p>\n\n\n\n Partners<\/strong>: Software Competence Center Hagenberg<\/a> (SCCH), Radon Institute of Computational and Applied Mathematics<\/a> (RICAM), Research Institute for Symbolic Computation<\/a> (RISC), Institute for Machine Learning<\/a> (IML), Computer Security and Industrial Cryptography – KU Leuven<\/a> (COSIC)<\/p>\n\n\n\n Budget<\/strong>: 3750000 \u20ac<\/p>\n<\/div><\/div>\n\n\n\n RexLearn project<\/strong> – Reliable and Explainable Adversarial Machine Learning<\/strong><\/a> (August 2019 – August 2023)<\/p>\n\n\n\n Supported by the Italian Ministry of Education, University and Research (MUR) within the PRIN2017, the project posed three main challenges<\/strong> that are hindering current progress towards the development of secure machine-learning technologies<\/strong>, and advocate the use of novel methodological approaches to tackle them: 1. The challenge of security evaluation; 2. The challenge of countering adversarial examples; 3. The challenge of designing interpretable machines.<\/p>\n\n\n\n People involved<\/strong>: <\/a>Fabio Roli<\/strong><\/a>, Battista Biggio<\/a>, Marco Melis, Maura Pintor,<\/a> Ambra Demontis<\/a><\/p>\n\n\n\n Partners<\/strong>: University of Venice \u201cCa\u2019 Foscari\u201d<\/a>, University of Florence<\/a>, University of Siena<\/a><\/p>\n\n\n\n Budget<\/strong>: 914640 \u20ac<\/p>\n<\/div><\/div>\n\n\n\n BullyBuster – A framework for bullying and cyberbullying action detection by computer vision and artificial intelligence methods and algorithms<\/a><\/strong> (August 2019 – August 2023)<\/p>\n\n\n\n Supported by the Italian Ministry of Education, University and Research (MIUR) within the PRIN2017, the project has been included in the Global Top 100 list of AI projects addressing the 17 UNS-DGs (United Nations Strategic Development Goals) by the International Research Center for Artificial Intelligence under the auspices of UNESCO.<\/p>\n\n\n\n People involved: Gian Luca Marcialis<\/strong><\/a>, Giulia Orr\u00f9<\/a>, Marco Micheletto<\/a>, Sara Concas<\/a>, Gianpaolo Perelli<\/a><\/p>\n\n\n\n Partners: University of Bari Aldo Moro<\/a>, University of Foggia<\/a>, University of Naples Federico II<\/a><\/p>\n\n\n\n Budget: 1.056.819,14 \u20ac<\/p>\n<\/div><\/div>\n\n\n\n IMMAGINA – IMaging MAnagement Guidelines and Informatics Network for Law Enforcement Agencies<\/a> <\/a><\/strong>(November 2020 – December 2022)<\/p>\n\n\n\n Supported by the European Space Agency (ESA)<\/a> within the ARTES Integrated Applications Promotion Programme<\/p>\n\n\n\n People involved: Fabio Roli<\/strong><\/a>, Giorgio Fumera<\/a>, Lorenzo Putzu<\/a>, Rita Delussu<\/a>, Emanuele Ledda<\/a><\/p>\n\n\n\n Partners: REGOLA SRL<\/a>, Digisky<\/a>, Planetek Italia SRL<\/a>, Stratobotic SRL<\/a>, Alfa Bit Omega SRL<\/a><\/p>\n\n\n\n Budget:<\/p>\n<\/div><\/div>\n\n\n\n HistoDSSP – Histopathological Decision Support System for Pathology<\/a><\/strong> (October 2018 – September 2020) <\/p>\n\n\n\n Funded by Sardegna Ricerche<\/a> under the ‘Aid for research and development projects’ program (POR FESR Sardegna 2014-2020).<\/p>\n\n\n\n People involved: Giorgio Fumera<\/strong><\/a>, Lorenzo Putzu<\/a><\/p>\n\n\n\n Partners: SmartPath<\/a><\/p>\n\n\n\n Budget: 570458.40 \u20ac<\/p>\n<\/div><\/div>\n\n\n\n LETSCROWD EU project <\/strong><\/a>(May 2017 – October 2019)<\/p>\n\n\n\n LETSCROWD (Law Enforcement agencies human factor methods and Toolkit for the Security and protection of CROWDs in mass gatherings) is a project funded by the European Commission under the HORIZON 2020 Programme.<\/p>\n\n\n\n People involved: Fabio Roli<\/a>,<\/strong> Giorgio Fumera<\/a>, Davide Ariu, Matteo Mauri, Rita Delussu<\/a>, Lorenzo Putzu<\/a><\/p>\n\n\n\n Partners: <\/strong>ETRA Investigaci\u00f3n y Desarrollo S.A.<\/a> (Spain), Polic\u00eda Municipal de Madrid \u2013 Ayuntamiento de Madrid<\/a> (LEA-Spain), University of Applied Sciences \u2013 Police Affairs<\/a> (LEA-Germany), Crowd Dynamics International Ltd<\/a> (UK), Deep Blue<\/a> (Italy), European Emergency Number Association<\/a> (Belgium), Expert System Spa<\/a> (Spain), Local Police Voorkempen \u2013 Lokale Politie Voorkempen<\/a> (Belgium), Ministry of the Interior- Polizia di Stato, Department of Public Security<\/a> (LEA-Italy), PROPRS Ltd.<\/a> (UK), Ministerio da Administracao Interna – Pol\u00edcia de Seguran\u00e7a P\u00fablica<\/a> (LEA-Portugal), RAILSEC Ltd<\/a> (Israel), Ministry of Internal Affairs – Ministerul Afacerilor Interne<\/a> (LEA-Romania), Universidad de Cantabria<\/a> (Spain), Pluribus One<\/a> (Italy, DIEE’s third party partner).<\/p>\n\n\n\n Budget: 2919307 \u20ac<\/p>\n<\/div><\/div>\n\n\n\n AI-Textiles – Intelligenza Artificiale e Tessuti intelligenti: Tecnologie e Applicazioni <\/strong>(Febbraio 2018 – Novembre 2019)<\/p>\n\n\n\n AI-Textiles (Artificial Intelligence & electronic textiles) is funded by Sardegna Ricerche<\/a> within the “Top-Down Cluster Programme” (POR FESR Sardegna 2014\/2020).<\/p>\n\n\n\n People involved: Fabio Roli<\/strong><\/a>, Matteo Mauri, Luca Piras, Luca Didaci<\/a>, Alberto Dessena, Carla Piras<\/p>\n\n\n\n Partners: Faticoni,<\/a> Imedia<\/a>, Infora<\/a>, Passamonti<\/a>, Abacons<\/a>, Kappaten<\/a>, Nomadyca<\/a>, Tecnofor<\/a>, Datasystem<\/a>, Giunti Psychometrics<\/a>, Aicof<\/a><\/p>\n<\/div><\/div>\n\n\n\n FORC EU project <\/strong><\/strong>(October 2016 – October 2019)<\/p>\n\n\n\n FORC (Pathway in Forensic Computing) is a project funded by the European Commission under the ERASMUS+ programme.<\/p>\n\n\n\n People involved: Giorgio Giacinto<\/strong><\/a>, Davide Ariu, Igino Corona, Carla Piras<\/p>\n\n\n\n Partners: Middlesex University London<\/a>, Dublin City University<\/a>, Al-Quds University<\/a>, Palestine Technical University – Kadoorie<\/a>, Jordan University<\/a>, Princess Sumaya University for Technology<\/a>, Al Andalus Software Development (ASD)<\/a>.<\/p>\n\n\n\n Budget: 899213 \u20ac<\/p>\n<\/div><\/div>\n\n\n\n PISDAS <\/strong>(June 2016 – March 2019)<\/p>\n\n\n\n PISDAS (Piattaforma Integrata Servizi Digitali Avanzati Sicuri) is a project funded by Regione Autonoma della Sardegna<\/a> – Regional Government of Sardinia (POR FESR 2007\/2013 – PIA 2013 – industria, artigianato e servizi per la selezione di interventi a sostegno della competitivit\u00e0 e dell\u2019innovazione)<\/p>\n\n\n\n People involved: Giorgio Giacinto<\/strong><\/a>, Gian Luca Marcialis<\/a>, Davide Maiorca<\/a>, Mansour Ahmadi, Alessandro Medda<\/p>\n\n\n\n Partner: Innovery Spa<\/a><\/p>\n\n\n\n Budget: 185987 \u20ac<\/p>\n<\/div><\/div>\n\n\n\n A^3I <\/strong>(July 2015 – November 2018)<\/p>\n\n\n\n A^3I (Advanced Analysis of Aerial Images) is a project funded by Regione Autonoma della Sar<\/a>d<\/a>egna<\/a> – Regional Government of Sardinia (POR FESR 2007\/2013 – PIA 2013 – industria, artigianato e servizi per la selezione di interventi a sostegno della competitivit\u00e0 e dell\u2019innovazione)<\/p>\n\n\n\n People involved: Fabio Roli<\/strong><\/a>, Giorgio Fumera<\/a><\/p>\n\n\n\n Partners: Aeronike<\/a>, Kareltecnologie<\/a>, Passamonti<\/a>, Bittree<\/a><\/p>\n\n\n\n Budget: 607000 \u20ac<\/p>\n<\/div><\/div>\n\n\n\n DOGANA EU project<\/a><\/strong> (September 2015 – August 2018)<\/p>\n\n\n\n DOGANA “aDvanced sOcial enGineering And vulNerability Assessment” project has received funding from the European Union\u2019s <\/strong>Horizon 2020 Research and Innovation programme.<\/p>\n\n\n\n People involved: Fabio Roli<\/a><\/strong>, Matteo Mauri, Davide Ariu, Igino Corona, Alessio Mulas, Carla Piras<\/p>\n\n\n\n Partners: Engineering International Belgium<\/a>, <\/strong>Cefriel<\/a>, Austrian Institute of Technology<\/a>, Consorzio nazionale interuniversitario per le telecomunicazioni – CNIT<\/a>, Inov Inesc Inovacao – Instituto De Novas Tecnologias<\/a>, National Center For Scientific Research “Demokritos”<\/a>, University of Applied Sciences and Arts of Southern Switzerland – SUPSI<\/a>, KU Leuven<\/a>, PROPRS Ltd.<\/a>, VisionWare Sistemas de Informa\u00e7\u00e3o SA<\/a>, Thales Communications and Security SA<\/a>, Thales Services S.A.S<\/a>, Hewlett Packard<\/a>, ELTA Solutions Ltd<\/a>, Gabinete Nacional de Seguran\u00e7a<\/a>, Regia Autonoma de Transport Bucuresti<\/a>, Ministry Of National Defence – Greece<\/a>, Danish Institute of Fire and Security Technology – DBI<\/a><\/p>\n\n\n\n Budget: 4999558 \u20ac<\/p>\n<\/div><\/div>\n\n\n\n BS2R <\/strong>(May 2016 – May 2018)<\/p>\n\n\n\n BS2R (Beyond Social Semantic Recommendation) is industrial R&D project funded by Regione Autonoma della Sardegna<\/a> – Regional Government of Sardinia (POR FESR 2007\/2013 – PIA 2013 – industria, artigianato e servizi per la selezione di interventi a sostegno della competitivit\u00e0 e dell\u2019innovazione).<\/p>\n\n\n\n People involved: Giorgio Giacinto<\/strong><\/a>, Luca Piras, Lorenzo Putzu<\/a><\/p>\n\n\n\n Partners: CRS4<\/a>, Cons<\/a>ulthink<\/a><\/p>\n\n\n\n Budget: 329100 \u20ac<\/p>\n<\/div><\/div>\n\n\n\n Le strutture Computazionali Quantistiche al servizio del Pattern Recognition: modellare l\u2019incertezza (Quantum Computation Structures at the service of Pattern Recognition: modeling uncertainty)<\/strong> – <\/strong>(September 2013 – September 2016)<\/p>\n\n\n\n The project is funded by Regione Autonoma della Sardegna<\/a> (the regional Government of Sardinia).<\/p>\n\n\n\n People involved: Luca Didaci<\/strong><\/a>, Davide Ariu, Luca Piras<\/p>\n\n\n\n Budget: 300000 \u20ac<\/p>\n<\/div><\/div>\n\n\n\n
\n\n\n\n![\"\"](\"https:\/\/sites.unica.it\/pralab\/files\/2024\/03\/BullyBuster2.png\")
<\/a><\/figure>
\n\n\n\n![\"\"](\"https:\/\/sites.unica.it\/pralab\/files\/2024\/02\/sec4ai4sec-eu.png\")
<\/a><\/figure>
\n\n\n\n![\"\"](\"https:\/\/sites.unica.it\/pralab\/files\/2024\/02\/bully-buster-logo-ok-1024x480-3.png\"){kind=logo}
<\/a><\/figure>
\n\n\n\n![\"\"](\"http:\/\/sites.unica.it\/pralab\/files\/2024\/02\/s3AI_project_logo.png\"){kind=logo}
<\/a><\/figure>
The project is primarily oriented by fundamental research that aims to come up with: i) a mathematical framework for regularizing the hidden representations of the deep models during the learning phase to allow the derivation of error bounds and functionality guarantees; ii) robust transfer learning techniques to accelerate training; iii) distributed network architectures and learning schemes that guarantee privacy preserving; iv) analysis methodologies for assuring security and safety.<\/p>\n\n\n\n
\n\n\n\n![\"\"](\"https:\/\/sites.unica.it\/pralab\/files\/2024\/02\/bully-buster-logo-ok-1024x480-2.png\"){kind=logo}
<\/a><\/figure>
\n\n\n\n![\"\"](\"http:\/\/sites.unica.it\/pralab\/files\/2023\/06\/bully-buster-logo-ok-1024x480.png\"){kind=logo}
<\/a><\/figure>
\n\n\n\n![\"\"](\"http:\/\/sites.unica.it\/pralab\/files\/2023\/07\/immagina_logo.jpg\"){kind=logo}
<\/a><\/figure>
\n\n\n\n![\"\"](\"https:\/\/sites.unica.it\/pralab\/files\/2023\/07\/HistoDSSP.jpg\")
<\/a><\/figure>
\n\n\n\n![\"\"](\"http:\/\/sites.unica.it\/pralab\/files\/2023\/06\/letscrowd.png\")
<\/a><\/figure>
\n\n\n\n![\"\"](\"https:\/\/sites.unica.it\/pralab\/files\/2023\/06\/AITextiles.png\")
<\/figure>
\n\n\n\n![\"\"](\"https:\/\/sites.unica.it\/pralab\/files\/2023\/06\/forc_img.png\")
<\/figure>
\n\n\n\n![\"\"](\"https:\/\/sites.unica.it\/pralab\/files\/2023\/06\/PISDAS.png\")
<\/figure>
\n\n\n\n![\"\"](\"http:\/\/sites.unica.it\/pralab\/files\/2023\/06\/cropped-vGEYfshd_400x400-1.png\")
<\/figure>
\n\n\n\n![\"\"](\"https:\/\/sites.unica.it\/pralab\/files\/2023\/06\/dogana.png\")
<\/a><\/figure>
\n\n\n\n![\"\"](\"https:\/\/sites.unica.it\/pralab\/files\/2023\/06\/bs2r-1.png\")
<\/figure>
\n\n\n\n![\"\"](\"http:\/\/sites.unica.it\/pralab\/files\/2023\/06\/cropped-cropped-vGEYfshd_400x400-1.png\")
<\/figure>
\n\n\n\n
![\"\"](\"https:\/\/sites.unica.it\/pralab\/files\/2023\/06\/cyberRoad_resize.png\")
<\/figure>