Overview

The Proofpoint NexusAI Machine Learning has been part of the Proofpoint DNA for over 10 years. We leverage many AI and ML techniques to offer a cutting-edge, people-centric approach to security.

Proofpoint NexusAI employs many techniques to detect the many targeted threats such as BEC, EAC, phishing, cloud attacks, multi-stage attacks, etc. For example, payload less email fraud attacks are difficult to detect. This year we introduced Supernova, a new detection that leverages inbound and outbound gateway telemetry, supply chain risk analytics, and API data from cloud productivity platforms like Office 365 and Google Workspace to uncover even the most sophisticated email fraud attacks.
We also leverage our NexusAI with our internal threat researchers. They use the NexusAI tools to better understand incidents as well as find like-incidents.

AI and ML systems are only as good as the data that trains them. Proofpoint is unique in that we gather proprietary threat data from leading enterprises across the Fortune 1000, ISPs and hundreds of thousands of SMBs. We also gather data from across multiple attack vectors such as email, cloud, network and social media:

● 35B+ daily URLs scanned
● 22M+ cloud accounts monitored
● 6k+ worldwide IDS sensors
● 400-600k unique daily malware samples
● 400M+ domains monitored
● 112k+ social media accounts monitored

Data gathered across industries and geographies is fed into the multi-trillion data point Nexus Threat Graph to train our NexusAI. Everything learned from the data is then fed back into Proofpoint products. This means leveraging the data from AI and ML models to our entire customer base for insights like risk benchmarking, threat actor objectives & insights, and campaigns & attack patterns. We continue to build more reporting using this data for our customers to provide context and details about their unique threat landscape with a people-centric lens.