QuantumVentura
Contact

Home/Systems/CyberNeuro-RT

Cinematic

Network defense

CyberNeuro-RT

An IoT, AI/ML-driven, highly-scalable, real-time network defense and threat intelligence tool with CPU, GPU or low-power neuromorphic chip deployment.

Talk to the team How it works
06

ML algorithm ensemble

75×

dataset growth in under 2 months

02

neuromorphic offerings, Intel and Brainchip

How CyberNeuro-RT detects, what it trains on, where it runs, and how it presents what it finds.

02S01

04 points

Cutting-Edge Unsupervised ML

  • 01Scalable Unsupervised Outlier Detection (SUOD)
  • 026 ML algorithm ensemble
  • 03Model approximation for complex models
  • 04Variational Autoencoder (VAE), trained to minimize reconstruction error of initial input and reconstructed output

03S02

04 points

Proprietary Pipeline Adapts to Any Dataset

75x dataset growth in under 2 months.

  • 01Existing dataset ingestion: proprietary system enables ingestion of any existing network capture dataset with flexible support for any labelling system
  • 02From-the-wild zero day sampling: system enables capturing and simulation of novel threats for additional data sampling
  • 03Data generation via simulation: ThreatATI database and proprietary ingestion system enable sampling and augmentation for cataloged threats from proprietary and public threat databases
  • 04Follow threats home with dark web tracking

04S03

04 points

At-the-edge Neuromorphic Processing

Two offerings from the leading neuromorphic developers: Intel and Brainchip.

  • 01Small form factor, magnitudes less power consumption than GPU
  • 02On-chip learning for deployment network specific attack detection
  • 03Intel Loihi
  • 04Brainchip Akida

05S04

03 points

Dashboards Minimize Operator Fatigue

A robust, multi-faceted, user-friendly cyber analyst dashboard prevents operator fatigue that allows cyber attacks to happen. Large numbers of false alarms cause real threats to be missed, and false alarms fatigue the cyber analyst, further increasing the risk of missed threats.

  • 01AI based false alarms are minimized, trained for minimal false positive rate
  • 02Possible threats are ranked by importance and confidence
  • 03Only the most relevant and likely alarms are actioned upon

06Detail

04 entries

Partners, funding and position.

Partners
Lockheed Martin Co. MFC Division · Pennsylvania State University
Funding
Partial funding from the U.S. Department of Energy
Deployment
CPU, GPU or low-power neuromorphic chip
Neuromorphic
Intel Loihi · Brainchip Akida

Provenance

A Quantum Ventura, Lockheed Martin, and Penn State Innovation. CyberNeuro-RT (CNRT) has been developed in partnership with Lockheed Martin Co.'s MFC Division and Pennsylvania State University under partial funding from the U.S. Department of Energy.

07Next

Two other systems