Projects

MAVEN (Management and Authenticity Verification of multimedia contENts) is a collaborative project among seven european partners, which  has been selected by the European Commission as one of the projects funded under the “Research for the benefit of SMEs” programme, in the 7^th Framework Programme. The focus of this programme is to foster applied research driven by the needs of small and medium-sized companies, with the aim of producing a positive impact on their business in the short term. As for MAVEN, its technical goal is to develop market-ready, efficient and robust tools for the management and authenticity verification of multimedia contents.

Why MAVEN? Despite the advances in the Security and Media sectors, MAVEN arises from the need of providing such industries with a suite of advanced technological solutions, able to operate in a range of realistic scenarios (CCTV, web images, broadcast data, etc).  The project results will allow SMEs, law enforcement bodies, press agencies, insurance companies and broadcasting companies, among others, to manage their multimedia assets and verify its integrity and authenticity, all in an efficient and scalable manner.

What will MAVEN do? MAVEN project will develop of a set of tools for  multimedia data management and security. The project’s objectives will be centered on two key concepts: “SEARCH” and “VERIFY”, both integrated in a coherent manner. This “search and verify” concept is not supported in an integrated manner by any tool currently available in the market.

Official website: http://maven-project.eu

Research areas: Multimedia Classification and Retrieval, Video Surveillance and Ambient Intelligence, Biometric Recognition

People involved: Fabio Roli, Davide Ariu, Ignazio Pillai, Giorgio Giacinto, Gian Luca Marcialis, Luca Piras, Roberto Tronci, Luca Ghiani, Giorgio Fumera, Matteo Mauri

Partners: Gradiant, CNIT (University of Siena e University of Florence), Amped Software, Playence, Arthaus, Xtream

Budget (€): 1010000

 

 

TABULA RASA is a project funded by the European Commission, under the Seventh Framework Programme. The TABULA RASA project will address some of the issues of direct (spoofing) attacks to trusted biometric systems. This is an issue that needs to be addressed urgently because it has recently been shown that conventional biometric techniques, such as fingerprints and face, are vulnerable to direct (spoof) attacks.

Official website: http://tabularasa-euproject.org/

Research areas: Biometric Recognition

People involved: Gian Luca Marcialis, Fabio Roli, Luca Ghiani, Valerio Mura, Matteo Mauri

Partners: Starlab Barcelona S.L., Sagem Sécurité, KeyLemon SA, Biometry.com AG, University of Oulu, Universidad Autonoma de Madrid, University of Southampton, Idiap Research Institute, Eurecom, Institute of Automation, Chinese Academy of Sciences (CASIA), Centre for Science Society and Citizenship - CSSC

Budget (€): 4000000

 

 

The GIEDION project (Gestione Intelligente e sicura di sEnsoristica Distribuita e della sua Interazione uOmo-macchiNa: possibili scenari futuri) is funded by Regione Autonoma della Sardegna - Regional Government of Sardinia (POR FESR 2007/2013 - PIA 2013 - industria, artigianato e servizi per la selezione di interventi a sostegno della competitività e dell’innovazione). Project objectives: intelligent and secure management of distributed sensors and related man-machine interaction, through the application of automated methodologies and machine learning techniques to some possible future scenarios (e.g. real time localisation through video-surveillance of risk areas; access to cloud data through biometric identification).
Video demo available on the PRA Lab youtube channel.
Official website: http://giedion.akhelab.com

Aree di ricerca: Biometric Recognition

People involved: Gian Luca Marcialis, Luca Ghiani, Valerio Mura, Giulia Orrù, Simona Tocco, Pierluigi Tuveri

The sTATA project is funded by Sardegna Ricerche within the "Top-Down Cluster Programme" (POR Sardegna FESR 2007/2013). The goal of the project is the creation, on the regional territory, of a district with specific and advanced know-how on computer and information security, within which the creation of approaches, solutions, and products that are secure "by design" can be fostered.

 

 

The GamI project is funded by Sardegna Ricerche within the "Top-Down Cluster Programme" (POR Sardegna FESR 2007/2013). The project aims to promote interaction between ICT companies, in order to acquire knowledge and skills studied by the Computer Vision and Machine Learning for the creation of innovative systems based on game devices that use Human-Machine-Environment interactions.

Official website: http://gami.diee.unica.it/

Research areas: Ambient Intelligence

People involved: Fabio Roli, Roberto Tronci, Alberto Dessena, Matteo Mauri

Partners: Experteam, Faticoni, Flosslab, Imedia, Infora, Logus, Nomadyca, Passamonti, Porcovino, Sa corona arrubia, Saime, Space

Budget (€): 138670

 

 

Pattern recognition systems will play a crucial role in the future Internet, and are already used in applications like biometric identity recognition and user preferences prediction. This makes them likely to be subject to several kinds of attacks by malicious users.

This project, funded by Regione Autonoma della Sardegna (the regional Government of Sardinia), aims at extending the theoretical foundations and the design methods of pattern recognition systems, including machine learning techniques, to adversarial environments, that are not taken into account by the classical theoretical framework.

Official website: http://secvpr.diee.unica.it/

People involved: Battista Biggio, Giorgio Fumera, Fabio Roli, Francesco Marra, Eyasu Zemene Mequanint, Rita Wong

Partners: Università di Napoli Federico II, Università Ca' Foscari Venezia, Università di Tubinga, Università del Surrey

Budget (€): 280000

Aim of the project Quantum Computation Structures at the service of Pattern Recognition: to model the uncertainty, funded by Regione Autonoma della Sardegna, is to use the body of knowledge of the quantum computational theories in an innovative way to address the problem of the uncertainty in the automatic recognition field in a uniform and consistent framework. The project aims to express and represent the basic concepts and algorithms of pattern recognition using the formal structures of the quantum computing. Particular attention will be given to practical applications of biometric recognition.

People involved: Luca Didaci, Davide Ariu, Luca Piras

Budget (€): 300000

 

 

 

I-Am is an industrial R&D project funded by Regione Autonoma della Sardegna (the regional Government of Sardinia). Its goal is to develop an innovative model of strong personal identity authentication based on the combination of multiple identity cues (e.g., a password and a biometric trait like a fingerprint), including the one-time password (OTP) technology.

3DCloudViz is an industrial R&D project funded by Regione Autonoma della Sardegna (the Regional Government of Sardinia), aimed at developing advanced technologies for remote visualization and execution of virtualized, interactive 2D/3D applications for technical computing.  (POR FESR 2007-2013).

People involved: Giorgio Fumera, Fabio Roli

Partner: Nice s.r.l.

Budget (€): 367800

 

Multimedia content is easily published and shared thanks to on-line social networks, such as Facebook, and to content sharing sites such as Flickr, TouTube, etc. To help users finding the contents of interest among this huge amount of multimedia data, this project aims at developing advanced techniques for the automatic classification and interactive retrieval of images and videos.

Unfortunately the popularity of content sharing sites also attracted the interest of attackers, that started distributing malware through documents and multimedia. Thus, multimedia content distribution and sharing requires advanced tools for the automatic analysis of files and network traffic to prevent users fall victim of computer attacks.

This project is funded by Regione Autonoma della Sardegna (the regional Government of Sardinia).

Research areas: Computer Security, Multimedia Classification and Retrieval

People involved: Giorgio Giacinto, Luca Piras, Davide Ariu, Igino Corona, Davide Maiorca

Partners: DISI - University of Trento, UPV Universitat Politècnica de València

Budget (€): 260000