Getty Images

Palo Alto announces ML-enabled software update and firewalls

Palo Alto's updated PAN-OS software uses machine learning to analyze network traffic in real time, and two firewall appliances provide the processing power to support it.

Palo Alto Networks has updated its PAN-OS software with in-line deep learning and AIOps capabilities and introduced two firewall appliances to work in tandem with the update.

The upgraded software, called PAN-OS 10.2 or Nebula, uses real-time cloud-based deep learning to analyze incoming traffic and identify threats, even when those threats don't resemble attacks already on record. The two new next-generation firewalls, the PA-3400 and the PA-5400, offer greater processing power to support the latency needs of traffic to and from the cloud for analysis.

Nebula differentiates itself from the previous versions of PAN-OS in two significant ways. First, it uses deep learning rather than static machine learning to analyze traffic threats. Deep learning processes significantly more data, allowing the AI to identify threats other than those that closely resemble recorded attacks.

Second, Nebula analyzes network traffic in real time. Palo Alto's previous machine learning (ML)-powered next-generation firewalls also sent suspicious traffic to the cloud for analysis but processed that traffic with a delay of minutes to hours.

By using deep learning in real time, Nebula boasts prevention that is six times faster and detects 48% more evasive threats than the previous version of PAN-OS, according to Palo Alto.

The PA-3400 is for edge and small campus deployments and the PA-5400 for large campus deployments and data centers. The appliances boast security performance three times better than previous generations of Palo Alto firewall appliances, the company said.

Although Palo Alto's next-generation firewalls will face competition from vendors like Cisco, Check Point and Fortinet, John Grady, an analyst at Enterprise Strategy Group, said Palo Alto's focus on ML is a consistent differentiator. While SASE security is growing, enterprises still need appliance-based firewalls for the data center. 

"I do think [ML for firewalls] is where the market's going; it's where everyone's working toward," Grady said. "[Palo Alto] pushing these detections in line on real traffic is a big step."

Palo Alto has also announced AIOps for next-generation firewalls to provide insights into a network's security posture and functionality. The company's 10th subscription service joins other security features like advanced URL filtering, DNS security and IoT security.

The Nebula update is available for any Palo Alto devices running the PAN-OS software. The PA-3400 and PA-5400 will be available in March.

Enterprise Strategy Group is a division of TechTarget.

Madelaine Millar is a news writer covering network technology at TechTarget. She has previously written about science and technology for MIT's Lincoln Laboratory and the Khoury College of Computer Science, as well as covering community news for Boston Globe Media.

Dig Deeper on Network security

Unified Communications
Mobile Computing
Data Center