Department of Electrical and Electronic Engineering


Dr. Luca Didaci is Assistant Professor of Computer Engineering at the University of Cagliari, Italy. He obtained the MS degree in Electronic Engineering in 2001, and the Ph.D. degree in Computer Engineering in 2005. He currently is with Dept. of Electrical and Electronic Engineering, and since 2001 he joined the research laboratory on Pattern Recognition and Applications (PRA Lab http://pralab.diee.unica.it) of the Dept. of Electrical and Electronic Engineering, University of Cagliari, Italy.

 

The research activity of dr. Didaci takes place in the field of pattern recognition and its applications, and covers the following topics.

1)  Computer security. Intrusion detection systems (IDS) and antivirus aim to recognize “malicious” software and behavior on computers and computer networks. However, traditional systems have a high rate of false alarms and a rigidity that prevents the recognition of new attacks. Dott. Didaci worked on the study of new methods based on Machine Learning and Multiple Classifier Systems (MCS) characterized by an increase in accuracy and a better balance between the ability to generalize and the generation of false alarms. As part of the CyberROAD EU project, it has contributed to defining a methodology for the realization of research paths on IT security issues.

2) Study of Multiple Classifier Systems. The Multiple Classifier Systems (MCS) are a state-of-the-art approach for the design of classification algorithms and allow to overcome different limits of the traditional approach, based on the use of a single algorithm. In particular, we have investigated methodologies for creating classification systems, and diversity measures as a useful tool for their creation.

3) Semi-supervised learning. Semi-supervised learning aims at design a classifier system using bot labelled and unlabelled data, whereas traditionally the classification algorithms were based only on labelled data, i.e. data whose class is known. These methods have been extended to both multiple classifier systems and innovative systems in the field of biometric recognition.

4) Security and Biometric Recognition. Biometric systems aim to use physiological or behavioral characteristics for individual recognition. In this context, multimodal systems based on the automatic recognition of faces and fingerprints and systems based on the analysis of brain signals have been studied. In particular, the study of brain signals highlights the discriminating power of functional connectivity measurements obtained from the EEG signal for biometric identification. Finally, the safety properties of the automatic learning algorithms in the biometric field against specifically targeted attacks and the related countermeasures were studied.

Dr. Didaci is a member of the Pattern Recognition an Applications Lab (PRA Lab, http://pralab.diee.unica.it), of CVPL (Italian Association for Research in Computer Vision, Pattern Recognition and Machine Learning – ex GIRPR) and IEEE (Institute of Electrical and Electronics Engineers).

[Last update: May 14, 2019]

 

[Last update: June 27, 2017]

Questionnaire and social

Share on: