Наредни састанак Семинара биће одржан у уторак, 19. марта 2024. у сали 301ф Математичког института САНУ. У оквиру састанка планирана су два предавања. Прво предавање биће одржано са почетком у 13 часова.
Предавач: Stjepan Picek, Radboud University, The Netherlands
Насплов предавања: AI-ASSISTED SIDE-CHANNEL ANALYSIS: PROMISES AND PITFALLS
Апстракт: Side-channel attacks (SCAs) are powerful attacks based on the information obtained from the implementation of cryptographic devices. Profiling side-channel attacks received a significant amount of attention as this type of attack defines the worst-case security assumptions. In the last few years, the most explored profiling attacks are based on deep learning techniques. Such attacks are very powerful as they can break targets protected with countermeasures. They are also „easier“ to deploy as they do not require pre-processing and/or feature selection. In this talk, we will cover the developments in the last eight years, starting with simple multilayer perceptron architectures and finishing with language-based models for SCA.
Друго предавање биће одржано са почетком у 14.15. У питању је заједнички састанак са Семинаром за вештачку интелигенцију.
Предавач: Manuel Ojeda Hernandez, Matemática Aplicada, Universidad de Málaga, Málaga, Spain
Наслов предавања: FUZZY CLOSURE STRUCTURES OVER COMPLETE FUZZY LATTICES
Апстракт: Closure structures are crucial in Mathematics, particularly in Algebra and Topology. The emergence of fuzzy Formal Concept Analysis (FFCA) has created the necessity to define a fuzzy closure operator. This motivation prompted the study of fuzzy closure operators, fuzzy closure systems, and their interrelationships. Similarly, closure relations can be thoroughly examined within this framework. This talk will present the definition of closure structures in arbitrary fuzzy lattices and compare them with existing ones in the literature.
Напомена: Регистрациона форма за учешће на Семинару је доступна на линку:
https://miteam.mi.sanu.ac.rs/call/wnz6oyxsQsy29LfJA/MjQ__eH607WeAL9X7IFtUI98xdQQgVkp-ljiEKPPfXr
Уколико желите само да пратите предавање без могућности активног учешћа, пренос је доступан на линку:
https://miteam.mi.sanu.ac.rs/asset/YoqHWKALRkRTbK9So