Quantum Ventura, a San Jose-based provider of AI and ML research and technologies, is using BrainChip’s Akida technology to develop cyber threat-detection tools.

Australian firm BrainChip is a commercial producer of low power, digital, event-based, neuromorphic AI IP.

In a federally funded phase-two programme, Quantum Ventura is creating cyber-security applications for the US Department of Energy under the Small Business Innovation Research (SBIR) programme. The programme is focused on cyber threat-detection using neuromorphic computing, which aims to develop an approach to detect and prevent cyber attacks on computer networks and critical infrastructure using brain-inspired artificial intelligence.

“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, CEO of Quantum Ventura. “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 at BrainChip, added: “This project with the Department of Energy offers an ideal opportunity to demonstrate how Akida opens up new possibilities in cyber security, 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 and AI IP can find unknown, repeating patterns in vast amounts of noisy data, which is an asset in cyber threat detection. Once Akida learns what normal network traffic patterns look like, it can detect malware, attack signatures and other types of malicious activity. Because of Akida’s ability to learn on device in a secure fashion, without need for cloud retraining, it can quickly learn new attack patterns, enabling it to adapt to emerging threats.

BrainChip IP supports incremental learning, on-chip learning and high-speed inference with performance in micro watt to milli-watt power budgets, suitable for AI and ML devices such as intelligent sensors, medical devices, high-end video-object detection, and ADAS and autonomous systems.

Akida is an event-based technology that is lower power than conventional neural network accelerators, providing energy efficiency with high performance for partners to deliver AI products previously not possible on even battery-operated or fan-less embedded edge devices.

Headquartered in Silicon Valley, Quantum Ventura is creating technologies in the areas of AI and ML verification and validation, cyber security, secure mobile technology and HPC-driven big data analytics. Its R&D division, QuantumX Research Labs, provides technology to federal agencies and corporations throughout the USA.

BrainChip specialises in edge AI on-chip processing and learning. The company’s first-to-market, fully digital, event-based AI processor, Akida, uses neuromorphic principles to mimic the human brain, analysing only essential sensor inputs at the point of acquisition, processing data with efficiency, precision and economy of energy. It enables edge learning local to the chip, independent of the cloud, reducing latency while improving privacy and data security.

Akida neural processor IP, which can be integrated into SoCs on any process technology, has shown benefits on today’s workloads and networks, and offers a platform for developers to create, tune and run their models using standard AI workflows such as Tensorflow and Keras. In enabling effective edge compute to be universally deployable across real world applications such as connected cars, consumer electronics and industrial IoT, BrainChip says on-chip AI, close to the sensor, is the future.