Machine Learning is used not only to detect new malware, but also to create more efficient, harder to detect threats. Will the pros of machine learning outweigh the cons or will the cybersecurity equilibrium deteriorate? And how to explain what the AI does when it makes decisions? This time, we will look at outsmarting cyber-criminals as well as understanding the AI itself.

_Supported by

_Recording

_Speakers

juraj janosik eset

Juraj Jánošík

ESET

Juraj joined ESET in 2008 as a Malware Analyst, he holds a bachelor’s degree in Applied informatics and a master’s degree in Robotics, both from the Slovak University of Technology. Currently, he is the leader of ESET’s Automated Threat Detection and Machine Learning section at ESET’s Core Research and Development. He was a member of several international working groups focusing on botnet eradication (e.g. Dorkbot, Gamarue, 3ve, Emotet). He presented at several international private and public conferences including RSA, MWC and CARO.

martin tamajka

Martin Tamajka

KInIT

Martin Tamajka is a researcher and lead engineer at the Kempelen Institute of Intelligent Technologies. He focuses on research of novel methods of deep learning, as well as on increasing the transparency of neural networks through methods of explainability and interpretability. His past research also includes analysis of multidimensional medical images and images in general. He will talk about finding the right explainability algorithm that provides good explanations for a given model, task and data.

_Agenda

Language: English

5:00 pm
Welcome
5:10 pm
Presentation – Will machine learning improve or disrupt the cybersecurity equilibrium? - Juraj Jánošík (ESET)
5:40 pm
Presentation – I want to know "why" - towards understandable Explainable AI - Martin Tamajka (KInIT)
6:10 pm
Live Q&A – _Slido #better_ai

_Sign up

Past Meetups