An AI research company. Twelve years building what the Department of Defense and the Department of Energy ask for and cannot buy. Machine learning, cybersecurity, hyperspectral imaging, synthetic aperture radar, signal processing, metamaterials and hypersonics.
Real-time network defense built on a hybrid supervised and unsupervised deep learning engine. The same models deploy on CPU, GPU or low-power neuromorphic chips, so detection runs in a cloud core or on a sensor at the edge.
CyberNeuro-RT is a second layer of defense. It runs alongside the perimeter tools already in place and is built to reduce the likelihood of an intrusion succeeding, and to surface the ones that do sooner. No security product can make an intrusion impossible, and we do not claim otherwise.
Developed with Lockheed Martin's MFC Division and Pennsylvania State University, under partial funding from the U.S. Department of Energy.
Detects intrusions across high-performance computing networks with unparalleled efficiency.
Supports detection of known attack types including DoS, DDoS and ransomware.
Deployable across edge, hybrid or full cloud infrastructure to meet your needs.
Combines supervised and unsupervised deep learning for robust threat identification.
Real-time model updates and continuous retraining for evolving threats.
Interactive dashboards provide clear insights for efficient security operations.
Three programs in RF sensing, navigation and radar autonomy.
A compact onboard sensing package that locates and identifies radio-frequency emitters from unmanned aircraft, holding its accuracy in cluttered signal environments.
A compact phased-array system that uses existing radio transmissions as navigation references, giving fast-moving vehicles an independent source of position data.
A low-cost radar sensing approach that gives autonomous vehicles perception and navigation where cameras and lidar fall short, in darkness, dust and poor light.
One product line, from real-time network defense through to source code.
Real-time network intrusion detection on a hybrid supervised and unsupervised deep learning engine, deployable on CPU, GPU or neuromorphic silicon.
Read more →
Automated HPC-scale network anomaly monitoring and autonomous threat mitigation.
Read more →
AI-driven source code vulnerability detection, trained on mission-critical repositories.
Read more →Major programs running with the Navy, the Air Force, DARPA, the Missile Defense Agency, Homeland Security and the Department of Energy, alongside Lockheed Martin and the national laboratories.
An automated screening campaign that searches high-entropy alloy compositions for high-temperature strength and oxidation resistance together, narrowing a very large candidate space down to a shortlist worth making and testing.
Recovers gold, copper and other constituents of value from electronic waste electrochemically and at room temperature. 25% higher recovery, 75% less chemical reagent, 30% lower water and electrical cost, and no toxic emissions. Commercialised as E-RECOV.
Idaho National Lab · Colt Refining
A simulator that generates synthetic aperture radar imagery in real time, so detection and classification models can be trained and evaluated against scenarios that are impractical or too expensive to fly.
Lockheed Martin
A multifaceted operation. In government work you cannot be a single-focused company.
Quantum Ventura Inc.
Operations
Quantum Guru · Unit R40, Burjuman
Distribution and support
Engineering
We reply from San Jose, usually within two working days.
