Airgap Networks enhances its Zero Trust Firewall with ThreatGPT
Airgap Networks announced that it is bringing the power of AI to its Zero Trust Firewall with ThreatGPT.
Built on an advanced AI/ML model designed to protect enterprises from evolving cyber threats, ThreatGPT delivers a new level of insight and productivity for network security teams.
Perimeter firewalls struggle with today’s combination of a complex, dynamic endpoint architecture and the real-world pervasiveness of legacy systems and headless devices. Airgap ZTFW complements existing perimeter firewall infrastructure by adding a dedicated layer of microsegmentation and access in the network core to protect business-critical networks and devices.
With the addition of ThreatGPT, Airgap makes staying ahead of advanced threats even easier – by providing a simple-to-use AI-powered natural language query interface and a deep pool of ML security insights.
“With highly accurate asset discovery, agentless microsegmentation, and secure access, Airgap offers a wealth of intelligence to combat evolving threats”, said Ritesh Agrawal, CEO of Airgap. “What customers need now is an easy way to harness that power without any programming. And that’s the beauty of ThreatGPT – the sheer data-mining intelligence of AI coupled with an easy, natural language interface. It’s a game changer for security teams.”
ThreatGPT is available as part of the Airgap Zero Trust Firewall, which shrinks attacks surface, secures access to critical devices, and accurately discovers all assets in your environment. Uniquely in the industry, the Airgap ZTFW provides agentless segmentation, stopping any threats from spreading laterally from device to device or from one network layer to the next.
Integrating seamlessly into existing security infrastructure, the Airgap agentless ZTFW can even microsegment the old Windows servers, IoT devices, and headless machines so common in real-world networks.
ThreatGPT uses a combination of graph databases and GPT-3 models to provide even more powerful cybersecurity insights. GPT-3 models can analyze natural language queries to identify potential security threats, while graph databases can provide contextual information on traffic relationships between endpoints.
With natural language queries, security operators can ask questions in plain English, simplifying the query process and enabling a wider range of staff members to participate in security monitoring and incident response. A great example: “How many Windows 2007 servers are using vulnerable protocols in our infrastructure?” ThreatGPT lets you ask simple questions that yield powerful insights.