Videolectures
The Future of Security and Forensic Computing in the new Education 2.0 era and Emphasis in Globalisation
Lecture di Giorgio Giacinto durante ICTCS 2017 - International Conference on new Trends in Computing Sciences, 11-13 Ottobre 2017, Amman, Giordania. Dall'abstract della conferenza: the goal of the conference is to provide an international forum where international scientists from the different fields of computer science meet each other to exchange ideas on current challenges and results.
Adversarial Pattern Recognition
Tutorial tenuto da Fabio Roli e Battista Biggio durante ICCV 2017 - International Conference on Computer Vision, 22-24 Ottobre 2017, Venezia. Dall'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 tenuta dal Prof. Fabio Roli durante HUML 2016 - The Human Use of Machine Learning: An Interdisciplinary Workshop, 16 Dicembre 2016, Venezia. Dall'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 tenuta dal Prof. Fabio Roli durante ICPRAM 2016 - International Conference on Pattern Recognition Applications and Methods, 24-26 Febbraio, 2016, Roma. Dall'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 presenta l'articolo "Is Feature Selection Secure against Training Data Poisonin" (co-autori Xiao H., Brown G., Fumera G., Eckert C., Roli F.) durante la conferenza IMCL 2015 - International Conference on Machine Learning (ICML 2015) tenutasi a Lille, Francia, dal 6 all'11 luglio 2015.
L'articolo può essere consultato qui.
Poisoning attacks to compromise face templates
Fabio Roli presenta l'articolo "Poisoning attacks to compromise face templates" (co-autori Battista Biggio, Luca Didaci, Giorgio Fumera) durante la conferenza 6th IAPR Int'l Conf. on Biometrics (ICB 2013) tenutasi a Madrid, Spagna, dal 4 al 7 Giugno 2013.
L'articolo può essere consultato qui.
Evaluation of serial and parallel multibiometric systems under spoofing attacks
Gian Luca Marcialis presenta "Evaluation of serial and parallel multibiometric systems under spoofing attacks". articolo pubblicato agli atti della conferenza BTAS 2012 - The IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems.
Settembre 23-26, Washington DC, USA
In questa pagina è disponibile la pubblicazione.
Learning Sparse Kernel Machines with Biometric Similarity Functions for Identity Recognition
Battista Biggio presenta "Learning Sparse Kernel Machines with Biometric Similarity Functions for Identity Recognition" (co-autori Giorgio Fumera e Fabio Roli), articolo pubblicato agli atti della conferenza BTAS 2012 - The IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems. Settembre 23-26; Washington DC, USA. In questa pagina è disponibile la pubblicazione.
Poisoning Attacks against Support Vector Machines
Battista Biggio presenta "Poisoning attacks against Support Vector Machines" (co-autori: Blaine Nelson and Pavel Laskov), alla conferenza International Conference on Machine Learning (ICML), Edinburgo, 25 Giugno - 1 Luglio 2012. L'articolo mira a dimostrare la vulnerabilita' delle SVM (Macchine a vettori di supporto) e, piu' in generale, degli algoritmi di apprendimento automatico, di fronte alla contaminazione dei dati di addestramento. In questa pagina è disponibile la pubblicazione.
Three Hours on Multiple Classifier Systems
Il prof. Fabio Roli tiene una lezione sui sistemi di classificatori multipli durante la scuola "The Analysis of Pattern". Dall'abstract della lezione: 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. The concept of classifier “diversity”. The design cycle of a multiple classifier system...>>
In questo video, durante il Workshop on Applications of Pattern Analysis (Londra, 2010), Davide Ariu introduce brevemente HMMPayl, un network-based Intrusion Detection System che realizza la payload analysis con finalità di protezione da attacchi verso web server o verso le web application che essi ospitano.
Applicazioni correlate: HMMPayl
Publicazioni correlate: HMMpayl: An Intrusion Detection System Based On Hidden Markov Models
Lezione del Prof. Giorgio Giacinto su "Analysis of Patterns for Computer Security" tenuta durante la scuola The Analysis of Patterns, 2 ottobre 2009, Parco Scientifico e Tecnologico di Pula (CA).
