Applying Machine Learning to Network Security Monitoring by Alex Pinto
Using Security Intelligence To Mitigate Today's Real Threats by Ken Westin
Regardless of the advances in malware and targeted attacks detection technologies, our top security practitioners can only do so much in a 24-hour day. Triage using alert-based monitoring (from IPSes, SIEMs and such) is inefficient because they are lacking in expressiveness. So how can we better use data from exploration-based and data-rich monitoring tools (such as threat intelligence feeds and network forensics) to effectively triage incidents for our teams to investigate?
Enter the use of Machine Learning as a way to automatically prioritize and classify potential events and attacks in your network. Statistical learning and data mining techniques can be used to automate the analysis of your logs and network data with threat intelligence and Internet topology, DNS, and WHOIS information.
This webcast will present examples and applications of these concepts and algorithms developed by MLSec Project in log data from public feeds and anonymized and summarized real live networks. Our objective is to demonstrate how these data-driven techniques can be used to help us transform our fire hose of available data into actionable intelligence.