Keynote Speaker

Abstract:

The use of robots has increased dramatically in recent years. Currently, there are multiple types of robots, from service robots, designed to help people in any kind of environment (home, work, hospitals…), to quadruped platforms, developed for critical infrastructures or the military field. Security in those platforms is crucial, since robots present vulnerabilities, they can pose a risk to both their integrity and that of the people/objects around them. In this work, a security evaluation of the Unitree A1, a quadruped robot, and the humanoid robot Pepper has been carried out, to know the security flaws that may be present, as well as the implications that it may have for the user, the environment, or the integrity of the robot. The ultimate goal of the work is that the vulnerabilities found will be taken into account by other researchers or companies that develop that kind of robot and take into account those security problems.

Biography:

Adrián Campazas Vega got his Ph.D. in Computer Science from the University of León in 2023. He got his degree in computer science (2015) and his master of science (2019) in Cybersecurity research at the University of León (León, Spain). From 2015 to 2019 he worked in different companies as an application developer and cybersecurity auditor. In 2020, he became part of a cybersecurity research project for the University of León. In addition, from the academic year 2019 to 2023 he has been lecturer in the area of computer architecture at the University of León.

Abstract:

In the rapidly evolving contemporary cyber threats landscape, hackers are pushing the boundaries of their craft aided by the prowess of artificial intelligence generative platforms like ChatGPT. Over the course of the year following its official release, ChatGPT and analogous AI-powered generative tools have emerged as instrumental aids for hackers seeking to engineer more sophisticated cyber threats. This article is devoted to the exploration of graph algorithms, synergizing them with the capabilities of AI and self-learning mechanisms, to proactively detect and counter ransomware and malware attacks. The core mission of this research is the development of an agile and resource-efficient model that not only outperforms existing benchmarks but also excels in early detection of ransomware and malware threats. By attaining this objective, the research aspires to establish a novel solution that demonstrates swifter responsiveness, optimal resource utilization, and the ability to discern both familiar and previously unseen forms of malicious cyber infiltrations.

Biography:

Stefan Tafkov is a young researcher in the field of cybersecurity and digital forensics. Holds a MSc degree on “Software Technologies” with specialization in AI from Plovdiv University “Paisii Hilendarski” where he is now also an invited lecturer on the problems of cybersecurity. MSc Tafkov is presently doing PhD thesis work in the field of Artificial Intelligence application for ransomware smart development & protection at IT for Security Department, Institute of ICT, Bulgarian Academy of Sciences. Longstanding junior collaborator of Joint Training Simulation & Analysis Center, Institute of ICT, Bulgarian Academy of Sciences. Entrepreneur in the computer & network security area. Author & co-author of several scientific papers in the field of cybersecurity. Holds various national & international distinguishes and awards for his achievements.

Abstract:

This research seeks to examine the dynamics of the Limit Order Book introducing a stochastic model for the limit order book in discrete time and space, driven by a symmetric random walk. Special attention is given to order avalanches, defined as sequences of order executions with periods of no trade events not exceeding ε > 0. The primary focus lies on the distribution of order avalanche lengths. Further, in order to access informativeness of order book data machine learning model based on the Gated Recurrent Unit (GRU) neural network is proposed and further studied. Additionally, the quantified results demonstrating the significant performance improvement achieved by selecting features based on the proposed feature selection methods are established.

Biography:

Dr Dragana Radojicic is specialized in financial mathematics and statistics, as well as in machine learning in finance. She received a B.Sc. degree in Mathematics from the University of Belgrade, Faculty of Mathematics in 2014. In 2016, she received M.Sc. degree in Mathematics at the Technical University of Berlin, as a scholarship holder and member of the Berlin Mathematical School (BMS). In September 2020, she received a PhD in Mathematics at the Faculty of Mathematics and Geoinformation, the Vienna University of Technology, where she had been working from 2016 until 2020 as a Teaching Assistant at the Department for Financial and Actuarial Mathematics.

She is an Assistant professor at the Faculty of Economics, University of Belgrade. She has published papers in highly rated journals and she has successfully presented her research at several international conferences. She teaches the following courses in the Bachelor studies: Sample Theory, Mathematical Statistics, Machine Learning, and Quantitative Finance, as well as in the Master’s studies for the course Data Mining and Machine Learning, and in the Doctoral studies Statistics 1D and Multivariate Analysis.