BrainChip Join Hands with Quantum Ventura To Develop Cyber Threat Detection By CIOTechOutlook Team

BrainChip Join Hands with Quantum Ventura To Develop Cyber Threat Detection

CIOTechOutlook Team | Tuesday, 16 May 2023, 08:44 IST

The AkidaTM technology from BrainChip Holdings Ltd, the first commercial manufacturer of ultra-low power, fully digital, event-based, neuromorphic AI IP in the world, will be used by Quantum Ventura Inc., a San Jose-based provider of AI/ML research and technologies, to create new cyber threat-detection tools.

Quantum Ventura is developing cutting-edge cybersecurity solutions for the U.S. Department of Energy as part of this federally supported phase 2 programme through the Small Business Innovation Research (SBIR) Programme. The program's main objective is "Cyber threat-detection using neuromorphic computing," which intends to provide a cutting-edge method to recognise and stop cyberattacks on vital infrastructure and computer networks.

“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.”

“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,” said Rob Telson, Vice President of Ecosystems & Partnerships at BrainChip. “We are excited about the progress that Quantum Ventura are making with BrainChip in this project which is extremely vital to the safety of the nation’s infrastructure.”

The Akida neural processor and AI IP are useful tools for detecting cyber threats because they can uncover obscure, recurring patterns in massive amounts of noisy data. Akida can identify malware, attack signatures, and other forms of harmful activity once it learns what typical network traffic patterns look like. The ability of Akida to securely learn on a device without the need for cloud retraining allows it to quickly pick up new attack patterns and fast adapt to new threats.

With unmatched performance in microwatt to milliwatt power budgets, BrainChip IP offers incremental learning, on-chip learning, and high-speed inference, making it the perfect choice for cutting-edge AI/ML devices such intelligent sensors, medical devices, high-end video-object identification, and ADAS/autonomous systems. Akida is an event-based solution that uses less power out of the gate than traditional neural network accelerators, combining great performance with energy efficiency.