Videolectures

The Future of Security and Forensic Computing in the new Education 2.0 era and Emphasis in Globalisation
Lecture  by Giorgio Giacinto during ICTCS 2017 - International Conference on new Trends in Computing Sciences, 11-13 October 2017, Amman, Jordan. The goal of the conference is to provide an international forum where international scientists from the different fields of computer science (Data mining, AI, IoT, and Computer Security) meet each other to exchange ideas on current challenges and results.
 
 
 
 
Adversarial Pattern Recognition
Tutorial given by Fabio Roli and Battista Biggio at ICCV 2017 - International Conference on Computer Vision, October 22-24, 2017, Venice. Abstract: "Learning-based pattern classifiers, including deep networks, are currently used in several applications, ranging from computer vision to computer security. Most of these applications, including spam and malware detection, differ from traditional machine learning tasks..."
 
 
 
 
 
Some thoughts on safety of Machine Learning
Talk given by Prof. Fabio Roli during HUML 2016 - The Human Use of Machine Learning: An Interdisciplinary Workshop, Venice, December 16th, 2016. From the abstract: "During the last forty years, machine learning research has been focused mainly on accuracy of algorithms, and occasionally on speed and scalability. Issues that are very important in mature engineering fields, like safety, reliability, testing, have been basically neglected. But something changed over the last five years..."
 
 
 
 
Adversarial Pattern Recognition
Talk given by Prof. Fabio Roli during ICPRAM 2016 - International Conference on Pattern Recognition Applications and Methods, February 24-26, 2016, Rome. From the abstract: "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.."
 
 
 
 
Is Feature Selection Secure against Training Data Poisoning?
Battista Biggio presents the paper "Is Feature Selection Secure against Training Data Poisonin", co-authored with Xiao H., Brown G., Fumera G., Eckert C., Roli F., during the IMCL 2015 - International Conference on Machine Learning (ICML 2015), held in Lille, France, from July 6th to July 11th, 2015.
The paper can be found here.
 
 
 
 
 
Poisoning attacks to compromise face templates
Fabio Roli presents the paper "Poisoning attacks to compromise face templates", co-authored with Battista Biggio, Luca Didaci, and Giorgio Fumera, during the 6th IAPR Int'l Conf. on Biometrics (ICB 2013) held in Madrid, Spain, from June 4th to June 7th, 2013.
The paper can be found here.
 
 
 
 
 
 
Evaluation of serial and parallel multibiometric systems under spoofing attacks
Gian Luca Marcialis introduces the paper "Evaluation of serial and parallel multibiometric systems under spoofing attacks", published in the proceedings of BTAS 2012 - The IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems. September 23-26; Washington DC, USA
 
 
 
 
 
Learning Sparse Kernel Machines with Biometric Similarity Functions for Identity Recognition
Battista Biggio introduces the paper "Learning Sparse Kernel Machines with Biometric Similarity Functions for Identity Recognition", co-authored with Giorgio Fumera e Fabio Roli, during the BTAS 2012 - The IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems. September 23-26; Washington DC, USA
 
 
 
 
Poisoning Attacks against Support Vector Machines
Battista Biggio introduces the paper "Poisoning attacks against Support Vector Machines," co-authored with Blaine Nelson and Pavel Laskov, at the International Conference on Machine Learning (ICML), Edinburgh, June 25 - July 1, 2012. The paper aims at demonstrating the vulnerability of SVMs (and, more generally, learning algorithms) under adversarial contamination of training data.
 
 
 
 
Three Hours on Multiple Classifier Systems
This lecture on "Analysis of Patterns for Computer Security" has been given by Prof. Fabio Roli during the school "The Analysis of Patterns", oct 2, 2009, Parco Scientifico e Tecnologico di Pula (CA). From the abstract of the lecture: Motivations and basic concepts Motivations of multiple classifier systems. The “worst” case and “best” case motivations. Practical and theoretical motivations. Basic concepts. Architectures for multiple classifier systems. Ensemble types, combiner types...>>
 
 
 
 
In this video Davide Ariu briefly introduces HMMPayl (an anomaly based Intrusion Detection System for the protection of a web server and of the applications the server hosts) during the spotlight session at the Workshop on Applications of Pattern Analysis, held in London (2010).
Related applications: HMMPayl
 
 
 
This lecture on "Analysis of Patterns for Computer Security" has been given by Prof. Giorgio Giacinto during the school "The Analysis of Patterns", oct 2, 2009, Parco Scientifico e Tecnologico di Pula (CA).