FireEye MalwareGuard Uses Machine Learning to Detect Malware
2.8.18 securityweek

FireEye on Tuesday announced the launch of MalwareGuard, an engine that leverages machine learning (ML) to detect malware and prevent it from executing.

MalwareGuard has been added to FireEye’s Endpoint Security product and the firm will also be deploying the new engine to its Network Security and Email Security solutions.

The engine is designed to predict whether a Windows executable file is malicious, prior to its execution. MalwareGuard should be able to detect both known malware and zero-day threats, FireEye said.

MalwareGuard is based on two years of research conducted by the company, which included assembling a dataset of more than 300 million samples and using it to train the engine. During its internal evaluation, which involved testing in real-world incident response cases, FireEye made predictions on over 20 million executable files.

“During the internal evaluation period, we also developed the infrastructure to support long-term tracking and maintenance for MalwareGuard,” FireEye said in a blog post. “Our goal was and is to have real-time visibility into the model’s performance, with the expectation that model retraining could be done on demand when performance dips below a threshold. To meet this objective, we developed data pipelines for each phase of the ML process, which makes the system fully automatable.”

The company’s blog post includes details on the goals, development, and testing of MalwareGuard.

In addition to MalwareGuard, FireEye informed customers that its Endpoint Security solution now includes new features designed to provide improved management capabilities and enable organizations to rapidly respond to important alerts.

MalwareGuard and the other new features have been added to the latest version of FireEye Endpoint Security, specifically version 4.5.