PRA Lab works on the development of next generation pattern recognition systems for real applications such as biometric authentication, text categorization, and intrusion detection in computer networks. PRA mission is to address fundamental issues for the development of future pattern recognition systems, in the context of real applications.
Many biometric recognition systems require using a small set of reference templates per client to save computational resources during client verification. PRA Lab's approach, Super-sparse Biometric Recognition, is capable of outperforming state-of-the-art methods both in terms of recognition accuracy and number of required reference templates, by jointly learning an optimal combination of matching scores and the corresponding subset of templates.
PRA Lab has 20 years experience on the development of next-generation Pattern Recognition systems. The Lab Director is Prof. Fabio Roli, IEEE and IAPR fellow. The Lab is made up of more than 30 people, including faculty members, post-doc researchers, PhD students and lab fellows. Research activities are carried out in the framework of regional, national, and european projects funded by public as well as private initiatives. Read more about our researchers.
"There is nothing more practical than a good theory".
Pra Lab develops many tools for computer security. SuStorID is an advanced Intrusion Detection System (IDS) for web services, based on machine learning. It demonstrates a number of interesting features, that can be readily exploited to detect and act against web attacks: Autonomous Learning - Anomaly-based Approach - Multi-model Architecture - Real-time Counteractions - Easy integration with modsecurity - Inspection of Encrypted traffic - User-friendly Interface.
Research at PRA Lab aims to develop secure-by-design systems, natively resilient against the attempts of evasion made by adversaries. The Lab activities focused on the “Adversarial Learning” area aim to study how the learning algorithms that empower our systems can be made more robust against these attempts by proactively simulating an arms race with the adversary to meet more strict security requirements.
Future Challenges in Cyber Crime and Cyber Terrorism Research: the CyberROAD perspective, May 25th
CyberROAD organizes its final event "Future Challenges in Cyber Crime and Cyber Terrorism Research: the CyberROAD perspective" at the Auditorium of the Faculty of Engineering and Architecture, University of Cagliari - Piazza d'Armi, Cagliari, Italy on May 25th, 2016.
Please register here (or from the form below) to help us better organise the event.
CyberROAD (Development of the Cybercrime and Cyber-terrorism Research Roadmap) is a project funded by the European Commission, under the Seventh Framework Programme. Cyber criminal activities are reported to be continuously growing and are negatively impacting the development of the European society and economy, and are pervasively affecting all the aspects of our daily lifes. Even though the level of awareness of cyber threats has increased, and Law Enforcement acts globally to fight against them, illegal profits have reached unsustainable figures. In addition to the economic reasons, however, cyber crime often hides other political and social motivations. In order to help coordinate the European efforts in the fight against cyber crime and cyber terrorism, the CyberROAD project has identified 19 research topics on which Europe should concentrate resources to increase its security and resilience, organizing them in strategic roadmap for Cyber Security Research. The CyberROAD project has been implemented by a consortium of 20 international partners, involved in the fight against Cyber Crime and Cyber Terrorism. Members include representatives from Academia and Research, Industry, Government and NGOs across Europe.
9:30-10:05: Networking Welcome Coffee 10:05-10:55: Opening Remarks - The CyberROAD Project Experience (The CyberROAD project,Fabio Roli, University of Cagliari; The CyberROAD roadmap,Enrico Frumento, CEFRIEL) 10:55-11:25: Selected Research Topics from CyberROAD: Cybercrime and Cyberterrorism Research Topics, Piotr Kijewski, NASK 11:25-11:55: Selected Research Topics from CyberROAD: Cybercrime and Cyberterrorism Research Topics,Jart Armin, CyberDefcon 11:55-12:25: The Joint CAMINO/COURAGE/CYBERROAD roadmap, Ben Brewster (CENTRIC - Sheffield Hallam University, COURAGE Project) 12:25-13:55: Networking Buffet Lunch 13:55-14:35: Cybersecurity needs in industry and industrial products,Michele Colaianni, University of Modena e Reggio Emilia 14:35-15:05: The Assessment of Systematic Security Risk in Interdependent Systems, Jens Grossklags, Penn State University 15:05-15:15: Closing remarks
National Tv Network Rai 3, "Buongiorno Regione", interview with Fabio Roli, Gian Luca Marcialis and Davide Ariu
Pra Lab on National TV RAI 3 (19/05/2016). Interview with Fabio Roli, Gian Luca Marcialis and Davide Ariu, about the research activities on Computer Security and Biometrics carried on at PRA Lab, University of Cagliari. Only Italian.
Each lesson will start at 2pm and will take 4 hours (June: 22th, 24th,27th,29th; July 1st). The lessons will be held in Mocci Room, Department of Electrical and Electronic Engineering, University of Cagliari.
This series of lectures is aimed to introduce the fundamentals of biometric technologies for personal recognition. A biometric system for personal verification is made up of the following modules: sensor, feature extractor, matcher. These modules will be described with respect to two biometrics: fingerprint and facial traits. Multi-modal biometrics, that is, systems which combine information from multiple biometrics, will be also presented. Finally, some open research issues will be introduced.
Pattern recognition systems are currently used in several applications, like biometric recognition, spam filtering, and intrusion detection in computer networks, which differ from the traditional ones. The difference lies in the fact that in these applications an intelligent, adaptive adversary can actively manipulate patterns with the aim of making the classifier ineffective, namely, with the aim of evading it. This kind of problem has been recently named adversarial classification, and is the subject of an emerging research field in the machine learning and pattern recognition communities. In this talk, I introduce the fundamentals of adversarial classification from the perspective of a designer of pattern recognition systems, and illustrate the concepts of adversary-aware classifier, security evaluation, and defence countermeasures, with examples from security applications like spam filtering and biometric recognition.
In this work we empirically show that our approach can reliably predict the performance of multibiometric systems even under never-before-seen face and fingerprint presentation attacks, and that the secure fusion rules designed using our approach can exhibit an improved trade-off between the performance in the absence and in the presence of attack. We finally argue that our method can be extended to other biometrics besides faces and fingerprints.... Read more >>
Android PRAGuard Dataset: as retrieving malware for research purposes is a difficult task, we decided to release our dataset of obfuscated malware. The dataset contains 10479 samples, obtained by obfuscating the MalGenome and the Contagio Minidump datasets with seven different obfuscation techniques. You can find more details in our paper. In order to obtain the dataset, please send an email to Davide Maiorca [davide(dot)maiorca(at)diee(dot)unica(dot)it] with the following subject: "[Android PRAGuard] - Request". Please, carefully follow the indications provided in the Dataset dedicated page. Read more >>
The ILLBuster Experience. The ILLBuster project results have been presented during a final workshop that took place on January 29, 2016 at TISCALI Auditorium. (event's details). ILLBuster is a project funded by the European Commission (DG-HOME), programme "Prevention of and Fight against Crime". Its goals is to develop an integrated system (ILLBuster) for the automatic discovery of illegal activities on the internet network. The system is thought to be a valuable tool to be used by LEAs in their activities of prevention of and fight against. Read more >>