RESEARCH AND DEVELOPMENT PROJECTS
sAIfer Lab research activities are carried on in the framework of regional, national, and european projects, funded by public as well as private initiative.
sAIfer Lab is constantly looking for new partners to develop innovative and stimulating projects.
To collaborate with us or submit your collaboration invitation to the sAIfer Lab, please submit your project proposal: [email protected]
Below is a non-exhaustive list of the most relevant research and development projects conducted in recent years by researchers from the PRA Lab and SmartLab separately or jointly.
Among more than 100 projects in 30 years, we selected the following 30 relevant R&D projects with these criteria: relevance (impact), importance (for the research community), international level (EU funded projects), chronology (we considered here the last 10 years).
CoEvolution – A Comprehensive trustworthy framework for connected machine learning and secure interconnected AI solutions
November 2024 – October 2027
HORIZON EUROPE programme (grant agreement n. 101168560). The project is developing an integrated security, trust, and robustness (STR) assessment solution that combines AI models with context awareness and an AI model bill of materials (AIMBOM), in order to establish a universal STR risk assessment and security assurance hub aligned with EU regulatory frameworks.
Budget: 5.999.688,75 €
Labs involved: PRA Lab
People involved: Battista Biggio (P.I.), Maura Pintor, Ambra Demontis, Matteo Mauri
Sec4AI4Sec – Cybersecurity for AI-Augmented Systems
October 2023 – September 2026
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.
Budget: 4.283.037,50 €
Labs involved: PRA Lab
People involved: Battista Biggio (P.I.), Maura Pintor, Ambra Demontis, Giorgio Piras, Fabio Brau, Daniele Angioni, Matteo Mauri
Arrowhead FPVN - Arrowhead Flexible Production Value Networks
June 2023 - August 2026
HORIZON Europe - Chips Joint Undertaking programme (grant agreement n. 101111977). The project ambition is doubling of the European industrial productivity in automotive, aerospace and green energy services, by applying autonomous and evolvable information interoperability for adaptive production networks, and by providing machine-interpretable content for stakeholders. The resulting technology will substantially impact manufacturing productivity and flexibility.
Budget: 26.981.269,25 €
Labs involved: SmartLab
People involved: Luca Oneto (CO-P.I.), Davide Anguita (CO-P.I.), Gianluca Sommariva, Gianluca Boleto
ELSA - European Lighthouse on Secure and Safe AI
September 2022 – August 2025
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.
Budget: 7.434.058,75 €
Labs involved: PRA Lab, SmartLab
People involved: Battista Biggio (P.I.), Fabio Roli (P.I.), Luca Oneto, Maura Pintor, Ambra Demontis, Luca Demetrio, Angelo Sotgiu, Simone Minisi, Matteo Mauri
TRITON - Generative Automation of Security Penetration Tests
October 2024 – October 2027
European Union, European Defence Fund program. Internet of Things (IoT), novel ICT and Operating Systems, and Artificial Intelligence (AI) systems, open-up new attack fronts and shift the attackers’ interest to more sophisticated techniques. TRITON's key idea is to build a wide‐ranging manifold of novel tools and strategies that enable next‐generation ICT systems and networks to perform automated and Artificial Intelligence (AI) driven security assessments at massive scale.
Budget: 484.375,00 €
Labs involved: SmartLab
People involved: Fabio Roli (P.I.), Luca Demetrio, Antonio Emanuele Cinà, Federico Simonelli, Matteo Mauri
SERICS Spoke 3 - Attacchi e difese
January 2023 – December 2025
The SERICS Foundation - Security and Rights in CyberSpace has scientific and technological research as its main purpose and makes use of a partnership for the management of numerous innovative projects. sAifer Lab researchers participates to several SERICS projects and research lines. In particular,UNICA (Professor Giorgio Giacinto) coordinates the Spoke 3 - Attacks and defenses project, within which the PRA Lab coordinates the research line "COVERT - In searCh Of eVidence of stEalth cybeR Threats" and the SmartLab coordinates the research line "SOS_AI - Science and engineering Of Security of Artificial Intelligence".
Budget: 8.500.000,00 €
Labs involved: PRA Lab, SmartLab
People involved: Giorgio Giacinto (Spoke 3 Coordinator and COVERT P.I), Pierangelo Loi, Leonardo Regano, Silvia Lucia Sanna, Lorenzo Pisu, Diego Soi, Davide Maiorca, Alessandro Sanna; Fabio Roli (SOS_AI P.I.), Battista Biggio, Giorgio Fumera, Maura Pintor, Luca Demetrio, Angelo Sotgiu; other SERICS Spokes: Gian Luca Marcialis, Giulia Orrù, Marco Micheletto, Roberto Casula, Luca Didaci
RAIDLab - Railway Artificial Intelligence and Data Analysis Laboratory
December 2018 - December 2028
The RAIDLab is a joint lab between the Hitachi Rail STS and the Department of Informatics Bioengineering, Robotics, and System Engineering (DIBRIS) of the University of Genoa (UNIGE). The objective of the RAIDLab is threefold: (i) training new professional roles with advance skills on AI for railway, (ii) push forward the state of the art in research of AI for railway, and (iii) deliver proof of concept and proof of value of AI in the field of railway.
Budget: 700.000,00 €
Labs involved: SmartLab
People involved: Luca Oneto (CO-P.I.), Davide Anguita (CO-P.I.), Luca Demetrio
Algorithmic Fairness
December 2018 – December 2028
Amazon Machine Learning Research Award for exploring and analyzing possible techniques to make ML algorithms capable of learning fairer models by utilizing empirical risk minimization theory.
Budget: 300.000,00 €
Labs involved: SmartLab
People involved: Luca Oneto (P.I.)
BullyBuster 2 – the ongoing fight against bullying and cyberbullying with the help of artificial intelligence for the human wellbeing
November 2023 – November 2025
Next Generation EU / 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.
Budget: 299.258,00 €
Labs involved: PRA Lab
People involved: Gian Luca Marcialis (P.I), Giulia Orrù, Marco Micheletto, Sara Concas, Simone Maurizio La Cava, Gianpaolo Perelli, Andrea Panzino
SAFER - Robust Models for Safe and Secure AI Systems
April 2024 – October 2025
Next Generation EU. The project aims to develop (i) scalable and systematic testing methodologies to evaluate adversarial and out-ofdistribution robustness beyond the simplistic perturbation models studied so far, considering moreadvanced, application-specific perturbations; and (ii) AI models that are more efficient and robust, also against more realistic and practical data manipulations.
Budget: 274.999,50 €
Labs involved: PRA Lab
People involved: Battista Biggio (P.I.), Giorgio Giacinto, Fabio Roli, Giorgio Fumera, Ambra Demontis, Gian Luca Marcialis.
SETA - Studying thE impact of anti-analysis Techniques in IoT security evAluations
November 2023 – November 2025
Next Generation EU / PRIN 2022 PNRR. The SETA project investigates anti-analysis techniques in IoT firmware. Vendors use these to protect intellectual property, but they can create security vulnerabilities. The project aims to detect and mitigate these strategies, providing a threat model for potential exploitation.
Budget: 229.240,00 €
Labs involved: PRA Lab
People involved: Giorgio Giacinto (P.I), Davide Maiorca, Battista Biggio, Alessandro Sanna
PAAM - Privacy Aware Anti Malware
November 2023 – November 2025
Next Generation EU / PRIN 2022 PNRR. The project aims to realize a Privacy-Aware Anti Malware (PAAM) framework, consisting of i) a Manifesto of requirements, ii) a framework of malware detection methods guaranteeing the user’s privacy, iii) an analysis of techniques that can be used for evading the PAAM Framework.
Budget: 255.884,00
Labs involved: PRA Lab
People involved: Giorgio Giacinto (P.I), Emmanuele Massidda
LivDet - Fingerprint Liveness Detection Competition
2009 – Ongoing
LivDet is a bi-annual competition that aims to assess the performance of the state-of-the-art fingerprint presentation attack algorithms according to a rigorous experimental protocol. The event is open to all academics, research centers and all companies that work in this field.
Labs involved: PRA Lab
People involved: Gian Luca Marcialis (P.I), Simone Carta, Roberto Casula, Marco Micheletto, Giulia Orrù
MLSec Seminars - Machine Learning Security Seminar Series
December 2022 – Ongoing
Curently co-funded by the ELSA project, HORIZON EUROPE programme (grant agreement n. 101070617). With more than 25 episodes aired since it’s started in 2022, this series of free online seminars has become a venue for discussing new developments in the field of machine learning security.
Labs involved: PRA Lab, SmartLab
People involved: Maura Pintor, Luca Demetrio, Battista Biggio, Angelo Sotgiu, Fabio Roli, Antonio Emanuele Cinà, Giorgio Piras, Ambra Demontis
S3AI – Security and Safety for Shared Artificial Intelligence by Deep Model Design
January 2020 – December 2024
S3AI is a COMET Module (Competence Centers for Excellent Technologies Programme), and funded by BMK, BMDW and the government of Upper Austria. The COMET Programme is managed by FFG.
The project is 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.
Budget: 3.750.000,00 €
Labs involved: PRA Lab
People involved: Battista Biggio (P.I.), Maura Pintor, Ambra Demontis
TrustML – Towards Machine Learning that Humans can Trust
September 2022 – October 2024
Funded by Fondazione di Sardegna. The project aims to address the main challenges that are hindering the development of trustworthy ArtificiaI Intelligence/Machine Learning models in these domains: 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.
Budget: 52.777,78 €
Labs involved: PRA Lab
People involved: Battista Biggio (P.I.), Giorgio Giacinto, Giorgio Fumera, Luca Didaci
RexLearn - Reliable and Explainable Adversarial Machine Learning
August 2019 – August 2023
Supported by the Italian Ministry of Education, University and Research (MUR), PRIN2017. The project posed three main challenges that are hindering current progress towards the development of secure machine-learning technologies, and advocate the use of novel methodological approaches to tackle them.
Budget: 914.640 €
Labs involved: PRA Lab
People involved: Fabio Roli (P.I.), Battista Biggio (P.I.), Maura Pintor, Ambra Demontis
BullyBuster – A framework for bullying and cyberbullying action detection by computer vision and artificial intelligence methods and algorithms
August 2019 – August 2023
Supported by the Italian Ministry of Education, University and Research (MUR), 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.
Budget: 1.056.819,14 €
Labs involved: PRA Lab
People involved: Gian Luca Marcialis (P.I), Giulia Orrù, Marco Micheletto, Sara Concas, Gianpaolo Perelli
DAYDREAMS - Development of prescriptive AnalYtics baseD on aRtificial intElligence for iAMS
December 2020 - 31 May 2023
HORIZON 2020 programme (grant agreement n. 101008913). Maintenance of the European railway network (300,000 km of tracks) is essential to ensure safety and sustainability. The project worked on the integration and use of data and artificial/human trustworthy intelligence together with a context-driven human machine interface (HMI), to allow context- and risk-aware multiple-options decision-making processes.
Budget: 1.700.000,00 €
Labs involved: SmartLab
People involved: Luca Oneto (CO-P.I.), Davide Anguita (CO-P.I.)
OPTIMA - cOmmunication Platform for TraffIc ManAgement demonstrator
December 2019 - April 2023
HORIZON 2020 programme (grant agreement n. 881777). OPTIMA project designed and developed a communication platform to manage the connection between several services supporting transportation management system (TMS) applications in the railway sector.
Budget: 2.200.000,00 €
Labs involved: SmartLab
People involved: Luca Oneto (CO-P.I.), Davide Anguita (CO-P.I.)
IMMAGINA - IMaging MAnagement Guidelines and Informatics Network for Law Enforcement Agencies
November 2020 – November 2022
Funded by ESA (ARTES Integrated Applications Promotion Programme), IMMAGINA supports law enforcement control rooms and public safety bodies with features based on aerial remote sensing and 5G technology, including early warning and mass alerting, fire prevention and management, and image and video analysis systems for crowd management and investigation support.
Budget: 1.361.316,00 €
Labs involved: PRA Lab
People involved: Giorgio Fumera (P.I), Lorenzo Putzu, Rita Delussu, Emanuele Ledda
FORC - Pathway in Forensic Computing
October 2016 - April 2020
EU Erasmus + Programme. The FORC project has sought to build and transfer capacities to develop integrated curricula in forensic computing as pathways within the undergraduate degrees of the faculties of Information Technology and Law, using a student-centred adaptive learning approach.
Budget: 899.213,00 €
Labs involved: PRA Lab
People involved: Giorgio Giacinto (P.I.)
IN2DREAMS - INtelligent solutions 2ward the Development of Railway Energy and Asset Management Systems in Europe
September 2017 - October 2019
HORIZON 2020 programme (grant agreement n. 777596). To support sustainable development of European railway infrastructures and its relating increase in freight and passenger services, novel data-driven ICT solutions were required. The project worked on monitoring, analysis, and exploitation of energy and asset information for the entire railway system, including the power grid, stations, rolling stock, and infrastructure.
Budget: 2.000.000,00 €
Labs involved: SmartLab
People involved: Davide Anguita (CO-P.I.), Luca Oneto (CO-P.I.)
LETSCROWD - Law Enforcement agencies human factor methods and Toolkit for the Security and protection of CROWDs in mass gatherings
May 2017 – October 2019
HORIZON 2020 programme (grant agreement n. 740466). To enhance the security and the protection of crowds during mass gatherings, the project produced a set of human centred tools for LEAs: real time crowd behaviour forecasting, innovative communication procedures, semantic intelligence applied to social networks and the internet, and novel computer vision techniques.
Budget: 1.361.316,00 €
Labs involved: PRA Lab
People involved: Fabio Roli (P.I.), Giorgio Fumera, Lorenzo Putzu, Rita Delussu, Matteo Mauri
DOGANA - aDvanced sOcial enGineering And vulNerability Assessment
September 2015 – August 2018
HORIZON 2020 programme (grant agreement n. 653618). The advent of Social Networks has made both companies and public bodies exposed to phishing and Social Engineering 2.0, and thus prone to targeted cyber-attacks. The project proposed a solution for a comprehensive assessment of Social Vulnerabilities arising from Social Engineering and for the reduction of the associated risks.
Budget: 4.999.558,00 €
Labs involved: PRA Lab
People involved: Fabio Roli (P.I.), Matteo Mauri
IN2RAIL - Innovative Intelligent Rail
May 2015 - April 2018
HORIZON 2020 programme (grant agreement n. 635900). IN2RAIL set the foundations for a resilient, consistent, cost-efficient, high-capacity European network by delivering important building blocks that unlocked the innovation potential in SHIFT2RAIL. The resulting concepts were embedded in a systems framework where infrastructure, information management, maintenance techniques, energy, and engineering were integrated, optimized and exploited.
Budget: 18.000.000,00 €
Labs involved: SmartLab
People involved: Davide Anguita (CO-P.I.), Luca Oneto (CO-P.I.)
CyberROAD - Development of the Cybercrime and Cyber-terrorism Research Roadmap
June 2014- May 2016
EU Seventh Framework Programme (grant agreement n. 607642). The main objective of CyberROAD was the development of the "Cybercrime and Cyber-terrorism research roadmap”. This roadmap was built through an in-depth analysis of all the technological, social, legal, ethical, political, and economic aspects on which cybercrime and cyber-terrorism are rooted.
Budget: 1.289.764,00 €
Labs involved: PRA Lab
People involved: Fabio Roli (P.I.), Giorgio Giacinto, Matteo Mauri
ILLBuster - Development of the Cybercrime and Cyber-terrorism Research Roadmap
February 2014 – February 2016
European Commission (DG-HOME), programme "Prevention of and Fight against Crime". The goal of the project was to develop an integrated information system for the semi-automatic discovery of illegal activities over the Internet, a valuable tool to be used by LEAs for their activities of prevention of and fight against cyber-crime.
Budget: 364.000,00 €
Labs involved: PRA Lab
People involved: Fabio Roli (P.I.), Giorgio Giacinto, Matteo Mauri
MAVEN - Management and Authenticity Verification of multimedia contENts
October 2013 – October 2015
EU Seventh Framework Programme (grant agreement n. 606058). The efficient management of large amounts of multimedia files is a challenging task in industrial environments. MAVEN arises from the need of providing advanced technological solutions to easily search contents within high populated galleries, and to verify that contents (and the information they convey) are genuine and thus credible.
Budget: 1.010.000,00 €
Labs involved: PRA Lab
People involved: Fabio Roli (P.I.), Giorgio Giacinto, Giorgio Fumera, Gian Luca Marcialis, Matteo Mauri
TABULA RASA - Trusted Biometrics under Spoofing Attacks
October 2011 – March 2014
EU Seventh Framework Programme (grant agreement n. 257289). The project addressed some of the issues of direct (spoofing) attacks to trusted biometric systems. Conventional biometric techniques, such as fingerprints and face, are vulnerable to direct (spoof) attacks.
Budget: 4.000.000,00 €
Labs involved: PRA Lab
People involved: Fabio Roli (P.I.), Gian Luca Marcialis, Matteo Mauri
