2024-12-14 –, Workshop Room 3
Come join RevEng as we discuss the role of machine learning in expediting the art of binary analysis culminating in a CTF designed to show case how these tools can be used.
So whether you are new, or a pro, to malware analysis and machine learning, we invite you to pop along, have some fun, and ask us as many questions as you'd like.
For over a decade security companies have been using machine learning to detect and protect against malicious binaries. Some have moved away entirely from traditional detection methods whilst others opt for a hybrid approach. Either way, sometimes they're right, sometimes they're wrong, and sometimes they've no idea what they've detected; luckily for them they've usually got security experts on hand.
Attribution, accuracy, similar samples? These questions often fall on the shoulders of security experts and all of which can be time consuming to answer. "Your customer insists the file isn't malicious, let me take a look at that in more detail.", "I might not find any other samples because there is nothing overly unique." or what about "It might be group [x] because these two binaries share a few similar strings...".
What if there was another way?
Join us as we explore leveraging machine learning to aide researchers in malware analysis, attribution and threat hunting before putting these skills into practice by completing a small CTF challenge aimed at show casing what we think the future of binary analysis will look like.
David started his career in developing and operating large scale analytical platforms aimed at providing cyber defense. Over the following decade, that focus shifted to defensive research and operations, most notably at Cylance and Blackberry and was the Global Director of Threat Research but has always maintained a hands on approach.
