ExtraHop Open Sources Machine Learning Dataset to help security teams detect malware and botnet operations faster

ExtraHop Open Sources Machine Learning Dataset to help security teams detect malware and botnet operations faster

ExtraHop, a leader in cloud-native network detection and response, has announced the open-sourcing of its expansive 16-million-row Machine Learning Dataset. The dataset aims to defend against domains generated by algorithm (DGAs), strengthening defenses against malware and botnet operations.

Amid a widening cybersecurity skills gap, up 26% in the last year, and dwindling resources, the cyber landscape is rapidly evolving. Open-sourced research and datasets are becoming solutions to the challenges security teams face daily.

“Collaboration among the cybersecurity community is invaluable: coming together to share our best work is the only way to remain on the offense and put attackers at a disadvantage,” said Raja Mukerji, Chief Scientist and Co-Founder at ExtraHop. “Our research will be a gamechanger for the community, and we encourage other teams to open source their own insights that will similarly benefit the industry at large.”

In an effort to foster industry collaboration, ExtraHop is releasing its DGA detector dataset on GitHub. The dataset, comprising over 16 million rows of data, will assist security teams in identifying malicious activity in their environments before these activities escalate into business problems.

DGAs are used by cyberthreat actors to maintain control within an organization’s environment after gaining access to a network. These tactics make cyberattacks difficult to detect and stop. Originally built for ExtraHop’s award-winning NDR platform, Reveal(x), the research can now be utilized by any security researcher. By constructing their own Deep Learning classifier model, they can more quickly identify DGAs and intervene in attacks with greater speed and precision. Since its implementation in Reveal(x), ExtraHop’s DGA model has demonstrated more than a 98% accuracy rate.

“Giving cyberthreat actors the ability to operate undetected has resulted in an uptick in these types of attacks. DGAs are increasingly considered a major threat to businesses today,” said Todd Kemmerling, Director of Data Science at ExtraHop. “We realized there was a lack of public datasets accessible to security teams with a diverse range of resources. This dataset fills that gap, giving any security team access to the crucial data needed to detect DGAs swiftly.”

Click below to share this article

Browse our latest issue

Intelligent CIO APAC

View Magazine Archive