Starzl PNT
Listens to ambient RF for a position fix. It doesn't transmit and it doesn't use GPS. The same observations map nearby emitters.
GPS is easy to lose
If the satellites are jammed or spoofed, most navigation stacks stop. Units still need a fix.
You also can't assume you'll have a network to pull a position from someone else.
The same listen-only feed that estimates your position also shows what's transmitting nearby.
Listen-only
Starzl PNT never transmits.
The same listen-only feed does two things. It figures out where you are without GPS, and it maps nearby transmitters — what they are, where they are, and how they move.
Those same observations also catch spoofing and man-in-the-middle attacks at the physical layer in under a second. The fix is computed on the device, so navigation keeps working when the network is down.
Specs
| Capability | Metric |
|---|---|
| Geolocation Accuracy | CEP50 < 10 m (outdoors, wooded environment) |
| Spoof detection | < 1 second |
| GPS Dependence | 0 satellites in the loop |
| Emission Signature | Zero — listen-only, no demodulation |
| Architecture | One process for position, emitter location, and spoof detection |
| Where the fix is computed | On the device |
One passive feed for navigation, emitter mapping, and spoof detection.
Typical path
Collect passively, detect emitters, localize, check for spoofing, and keep the fix.
Listens to whatever RF is already there. Nothing is transmitted.
Picks up what's already on the air — drone control, radar, radios — and builds a live map of who is transmitting and where.
Those transmitters produce your position. CEP50 < 10 m outdoors in woods. Each one is plotted on a map overlay.
Spoof and man-in-the-middle detection at the physical layer in < 1 second. Every fix is computed on the device.
The position estimate stays usable when the link is degraded or gone. No GPS satellites in the loop.
Related work
RF processing, adversarial AI, and operator training.
Compresses IQ, classifies emitters, and sends the result over a constrained link.
Starzl EW →Red-team tools for models and networks. The same stack is used on infrastructure defense.
Starzl Adversarial AI →Multi-day courses on AI, cyber, and OSINT. The skills stay useful when the software changes.
Starzl Operator Training →If you want to talk through a use case
Formerly fielded as GC3Sentry.