As federal agencies work to develop zero trust environments and stay ahead of the next major threat, merging AI with more traditional cybersecurity strategies could hold the key to progress.
In a webinar in May, two NVIDIA computer experts explained how the company has transformed itself in recent years into a full-stack company, with a range of powerful software applications. Chief among them, said NVIDIA Solutions Architect Jen Lombardo, is NVIDIA Morpheus, the company’s open-source AI cybersecurity framework, which she says “harvests the power of GPU computing to help protect your networks in a way never before seen.” was possible.”
Focusing on the Department of Defense (DoD) and the intelligence community (IC), Lombardo described how agencies are going through a transition similar to the company’s.
“The DoD and IC have long been focused on hardware, chips, planes and tanks and now these agencies are trying to make the leap into software-intensive ventures,” she said during the webinar, A New Look at Zero-Trust: An AI-Based Approach to Cybersecurityadding that senior defense officials emphasize that “to maintain a competitive advantage, our cyber defense must be the top priority.”
There is a lot of interest in the application of AI for cyber use cases, but at the same time, recently MeriTalk Research has found that many federal agencies struggle to move AI projects past the pilot phase.
Lombardo and Killian Sexsmith, senior developer relations manager at NVIDIA, explained that the Morpheus zero trust platform uses machine learning to identify and respond to threats that were previously impossible to identify, including phishing attacks and malware.
Lombardo and Sexsmith called the framework “accelerated computing and AI for cybersecurity,” Lombardo and Sexsmith said Morpheus performs all of these functions exponentially fast — data analysis 600 times faster than CPU-based alternatives, with improved accuracy and threat detection.
“New methodologies” and “new frameworks” are needed to meet the Office of Management and Budget’s zero trust implementation guidelines issued to federal civilian agencies in January, Lombardo said. This would require agencies to achieve a specific list of zero trust security targets by the end of FY 2024.
That’s where Morpheus comes in, Sexsmith said.
He dives into the details, saying that a key feature that sets Morpheus apart from other platforms is how it copes with phishing attacks. “What if we could analyze the entire raw body of the email?” he said. “What if we could look at both the syntax and semantics of the text when analyzing not just the words… an attacker uses, but how they structure the email? What are the subtle variations of legitimate emails we could detect?”
That’s exactly what Morpheus can do: analyze the entire body of an email, something Sexsmith says is out of reach for many systems, mainly due to computer limitations. The result, he said, is much more efficient detection of phishing attacks.
The same efficiency extends to Morpheus’ fraud detection system, which uses AI to better detect patterns in malicious transactions, Sexsmith said. Across the board, he added that the Morpheus framework — which NVIDIA first unveiled last year — detects cyber threats and responds faster, while allowing developers to write “orders of magnitude less code.”
These features, Sexsmith and Lombardo said, are especially needed at a time when the growing threat of increasingly sophisticated cyber-attacks makes the transition to zero trust more important than ever.
Access to the full presentation here†