Every GPS receiver
trusts the sky.
We're the software that tells it when not to.
We're the software that tells it when not to.
This is the interface behind the headline: a live replay of a spoof walk-off, the same feed an operator would watch on any platform under watch. No ambiguity, no dashboard to interpret.
All four checks agree. GPS is safe to feed to navigation.
Something is off. Signal health is slipping or checks mildly disagree.
Signal drowned out. Fixes are missing or too noisy to use.
The signal looks healthy but contradicts physics. Someone is lying.
On station-keeping flight, Navoro detects all three interference classes, instantaneous position spoofing, slow walk-off, and jamming, in 0.4 to 0.8 seconds. Walk-off is the one that matters: GPS position and velocity stay mutually consistent and the signal stays healthy, so no GPS-only check can see it. Ours does.
Every GPS fix is tested against what the vehicle's own sensors say is possible, whether it's a drone, a ground vehicle, a vessel, or an aircraft. Four independent checks, none of which trusts the GPS on its own, fused into a single score, with hysteresis, so one noisy frame never flips the state.
Does the reported motion match what the inertial sensors say the vehicle actually did? Teleporting fixes fail here instantly.
A short inertial estimate carried forward from the last trusted fix. Slow walk-off spoofs diverge from it and get caught.
An independent altitude channel the spoofer can't touch. GPS altitude has to agree with the air itself.
Carrier-to-noise and satellite count from the receiver. Jamming shows up here before positions even go bad.
One number, one state, every frame. Deterministic and pure: the same telemetry always produces the same verdict, which is exactly what you want when the verdict gets audited. Today that fusion is a documented weighted sum, not a black box, with a marked seam in the code for a learned model once we have the labelled data to train one responsibly.
Spoofing doesn't need to bring a vehicle down to win. It only needs to make navigation untrustworthy enough that an operator hesitates or grounds the fleet, so a system that only raises an alarm hands the attacker exactly that. The mitigation layer is built and tested, not just the detector.
When trust drops, the vehicle holds its last trusted position instead of following the spoofed one.
As position confidence keeps falling, it escalates automatically toward return-and-land.
A trusted position, an honest uncertainty budget, and a live countdown of how long the mission can safely continue.
# pure and deterministic. one Detection per frame
# pydantic v2 models as a frozen contract between components
from src.detector.engine import run
detections = run(frames, config)
# each Detection:
# trust_score: 0.0 to 1.0
# state: TRUSTED | DEGRADED | JAMMED | SPOOFED
$ make setup && make run
# then http://localhost:8000, pick a scenario, hit RunIt's a library, not a platform. Feed it telemetry frames, from a flight log or a live stream, and it returns a verdict for every frame. No hardware, no SDR, no cloud dependency.
Four canonical scenarios: clean flight, spoof jump, slow walk-off, jam corridor. Streamed onto a live map, colored by trust state as detections land.
Book the demoSee Navoro catch a spoof on your own platform.
Book the demo