Područje interesa Odjela za računalnu inteligenciju je teorija, oblikovanje, primjena i razvoj biološki i lingvistički motiviranih računalnih paradigmi s naglaskom na neuronske mreže, konekcijske sustave, genetičke algoritme, evolucijsko programiranje, neizrazite sustave i hibridne inteligentne sustave koji su temeljeni na ovim paradigmama.
Odjel za računalnu inteligenciju
Odjel za računalnu inteligenciju Hrvatske sekcije IEEE poziva Vas na predavanje:
Strojno učenje i evolucijsko računarstvo u kriptografiji
koje će održati dr. sc. Stjepan Picek u četvrtak, 13. listopada 2016. u 13:05 u prostoriji A202; predviđeno trajanje predavanja je 45 minuta.
Pozivamo i sve zainteresirane studente kojima je interesantno područje evolucijskog računarstva te strojnog učenja da dođu na predavanje.
Sažetak: U ovom predavanju ćemo istraziti kako upotrijebiti strojno učenje (ML) i evolucijsko računarstvo (EC) u kriptografiji. Predavanje ćemo započeti kratkim uvodom u relevantna područja i tada ćemo predstaviti jednu primjenu koja je našla svoje mjesto u praktičnim scenarijima. Točnije, govorit ćemo o ML i EC tehnikama i kako ih upotrijebiti u side-channel domeni. Side-channel napadi su svi napadi koji ne ciljaju na slabost kriptografskog algoritma, nego na njegovu implementaciju. U sklopu predavanja ćemo istražiti kako upotrijebiti nadzirano/nenadzirano/polu-nadzirano učenje te ćemo predstaviti koncept hijerarhijskog napada.
Konačno, dat ćemo kratak zaključak i raspravu koje su sličnosti i razlike kada se koriste iste tehnike s primjerom detekcije anomalija u mreži.
Životopis predavača dostupan je u nastavku obavijesti.
Title: Machine Learning and Evolutionary Computation in Cryptography
Abstract: In this talk, we investigate how to use machine learning (ML) and evolutionary computation (EC) techniques for applications in cryptography. We start with a short introduction on relevant areas and then we continue with one application that found its place in real-world scenarios. More specifically, we discuss how to use ML and EC in the side-channel attacks domain. Side-channel attacks are attacks that do not consider cryptographic strength of algorithms, but rather their implementations. We discuss how to use supervised/unsupervised/semi-supervised learning in this scenario as well as we introduce the concept of hierarchical attack.
Then, we offer a brief conclusion and we discuss what are the similarities and differences when using the same techniques in the security area with a case study in network anomaly detection.
CV: Stjepan Picek is a postdoc researcher in the Computer Security and Industrial Cryptography (COSIC) group at KU Leuven, Belgium.
He finished his PhD in 2015 as a double doctorate under the supervision of Lejla Batina, Elena Marchiori (Radboud University Nijmegen, The Netherlands) and Domagoj Jakobovic (Faculty of Electrical Engineering and Computing, Croatia). The topic of his research was cryptology and evolutionary computation techniques (EC) which resulted in a thesis "Evolutionary Computation in Cryptology". Currently, Stjepan is working as a postdoc researcher at the KU Leuven, Belgium as a part of the COSIC group where he continues with his research on the applications of EC in the field of cryptology.
Prior to that, Stjepan worked in industry and government.
He regularly publishes papers in both evolutionary computation (CEC, GECCO, EuroGP, PPSN,...) and cryptographic (CARDIS, COSADE, Indocrypt, SPACE, HOST,...) conferences.
Stjepan is also a member of organization committee for International Summer School in Cryptography and the vice-president of the Croatian IEEE CIS Chapter.
Besides that, he is a member of several professional societies (ACM, IEEE, IACR).
Stjepan serves as a reviewer for several journals and conferences.
Currently, he participates in the project funded by Croatian Scientific Foundation on Evolutionary algorithms in cryptographic applications.