<— Back

MAIMLA: Make artificial intelligence machine learning again

Although machine learning has been transforming the cybersecurity industry for decades, many people only start paying attention when buzzwords such as “artificial intelligence” enter the conversation. With the arrival of nextgen vendors, the technology itself was buried under layers of “silver bullet” marketing, obscuring its true contribution to threat detection. In our talk, we’ll try to cut through the noise and show how we’ve been deploying machine learning since the 1990s and how it has become a key component of our multilayered architecture. As a reality check, we will demonstrate how natural language processing methods (transformers) can help mitigate one of the admin’s worst nightmares – a destructive ransomware attack. For more context, we’ll venture into how adversaries use genetic and automation algorithms to create new variants of their malicious products. In the final section of our talk, we will describe potential threats that might leverage machine-learning technology in the foreseeable future.

Filip Mazán

Filip Mazán is a Senior Software Engineer and Team Lead at ESET. He joined ESET as a malware analyst in 2013, then switched to a software engineering role, and since 2019 has been leading a team responsible for automated threat detection and application of artificial intelligence in threat hunting. Some of the highlights of his career include speaking at the RSA Conference and membership in several botnet eradication groups taking on botnets such as Dorkbot and Gamarue. Currently, he is working on various machine-learning research projects leveraging deep learning. In his free time, Filip likes cooking, gardening and tinkering with home automation projects.