BrainChip and Quantum Ventura announced a partnership to develop new cyber threat detection tools that harness the power of artificial intelligence (AI) and machine learning (ML).
Quantum, a research and technology provider in AI and ML learning, has brought BrainChip’s Akida technology to a federally funded program to develop cybersecurity applications for the U.S. Department of Energy under the auspices of the Small Business Innovation Research (SBIR) program. We plan to apply it.
AI advances DOE cybersecurity
According to the companies, the SBIR program will focus on cyber threat detection using neuromorphic computing and aims to develop advanced approaches to detect and prevent cyber attacks against computer networks and critical infrastructure. and
Srini Vasan, President and CEO of Quantum Ventura, said of the impact of the partnership:
“Neuromorphic computing is an ideal technology for threat detection because of its small size, power, accuracy, and ability to learn and adapt, especially as attackers are constantly changing their tactics. We believe our solution incorporating BrainChip’s Akida represents a breakthrough in defending against cyberthreats, and is open to additional applications.”
Rob Telson, Vice President of Ecosystems and Partnerships at BrainChip added:
“This project with the Department of Energy is an ideal demonstration of how Akida opens up new possibilities for cybersecurity, including the ability to run complex AI algorithms at the edge to reduce reliance on the cloud. We are excited about the progress Quantum Ventura is making with the BrainChip, which is critical to the safety of the nation’s infrastructure.”
How BrainChip Akida works
The Akida neural processor can find unknown repeating patterns in large amounts of noisy data, which Brainchip says is an asset in cyberthreat detection. As Akida learns what normal network traffic patterns look like, it can detect malware, attack signatures, and other types of malicious activity.
Akida also learns on-device in a secure manner without requiring retraining in the cloud, allowing it to quickly learn new attack patterns and easily adapt to new threats.
BrainChip points out that Akida is an event-based technology that inherently consumes less power than traditional neural network accelerators. This enables energy efficiency with high performance to enable partners to deliver AI solutions previously not possible with battery-powered or fanless embedded edge devices.
