Detecting Attacks with Machine Learning

Presented by

Yariv Shivek

About this talk

Noise is the enemy of detection and response. After data breaches, forensic investigators have often found warning signs left behind by adversaries, but these signs were buried amongst thousands of other security alerts, including countless false positives. Machine learning and behavioral analytics can provide security teams the edge they need to reduce noise and accurately pinpoint attacks. Machine learning models can classify devices and compare current behavior to past behavior and peer behavior to isolate real attacks. Unlike static rules, machine learning models can dynamically adjust to ignore unusual but benign activity, drastically reducing false positives. Attend this informative session to understand: - Real-world examples of machine learning models used to detect attacks - The key shortcomings with today’s approaches to machine learning and how security best practices and the right tools can overcome them

Related topics:

More from this channel

Upcoming talks (2)
On-demand talks (930)
Subscribers (99709)
Palo Alto Networks is the next-generation security company, leading a new era in cybersecurity by safely enabling applications and preventing cyber breaches for tens of thousands of organizations worldwide. Built with an innovative approach and highly differentiated cyberthreat prevention capabilities, our game-changing security platform delivers security far superior to legacy or point products, safely enables daily business operations, and protects an organization's most valuable assets. Find out more at www.paloaltonetworks.com or call us at 1-877-524-1031.