Building Cyber Threat-Detection Tools with Neuromorphic Computing
This article is part of the TechXchange: Cybersecurity.
Quantum Ventura, a provider of artificial-intelligence (AI) and machine-learning (ML) research and technology solutions, will use BrainChip’s Akida technology to develop its next generation of cyber threat-detection tools. Quantum Ventura is addressing cybersecurity applications in a federally funded SBIR phase 2 program for the U.S. Department of Energy (DoE). It’s focusing on cyber threat-detection using neuromorphic computing to create an advanced approach to detect and prevent cyberattacks via brain-inspired AI.
“Neuromorphic computing is an ideal technology for threat detection because of its small size and power, accuracy, and in particular, its ability to learn and adapt, since attackers are constantly changing their tactics,” said Srini Vasan, President and CEO of Quantum Ventura Inc. “We believe that our solution incorporating BrainChip’s Akida will be a breakthrough for defending against cyber threats and address additional applications as well.”
Rob Telson, Vice President of Ecosystems & Partnerships at BrainChip, said, “This project with the Department of Energy offers an ideal opportunity to demonstrate how Akida opens up new possibilities in cybersecurity, including the ability to run complex AI algorithms at the edge, reducing the dependency on the cloud.
“We are excited about the progress that Quantum Ventura is making with BrainChip in this project, which is extremely vital to the safety of the nation’s infrastructure.”
The Akida neural processor with the optimal AI can find unknown repeating patterns in vast amounts of noisy data, and it can learn what normal network traffic patterns look like. Once in operation, it can detect malware, attack signatures, and other types of malicious activity without need for cloud retraining, quickly learning new attack patterns to adapt to emerging threats. The BrainChip IP supports the learning process.
Akida is an event-based technology that’s inherently lower in power consumption than conventional neural-network accelerators.
Read more articles in the TechXchange: Cybersecurity.
