Two years ago, an Endgame data scientist partook in a Kaggle competition. That work lead to Endgame’s MalwareScore. MalwareScore is a machine learning-based malware classifier used by our customers and has been scaled to be included in VirusTotal, scanning millions of files per day for viruses. The road from a fun weekend project to a real product is long and took tens of engineers and security experts. This talk describes this journey and highlights the many challenges of delivering a malware classification product.
The making of MalwareScore
Jonathan Woodbridge joined Endgame in 2015 after spending several years at Sandia National Laboratories. He received his B.S. from Georgia Tech and M.S. and Ph.D. from UCLA all in computer science. Jonathan’s research interests include approximate nearest neighbor techniques, pattern recognition, and neural networks. He has published over 20 academic papers, is the co-inventor on 4 patents, and was a recipient of the NIH/National Library of Medicine Medical Informatics Training Program Fellowship from 2009-2012.