UVS Detector

Under active development. UVS Detector is pre-release v1.0 — it ships when the system is ready, with no calendar promises. Full technical documentation and builds — by separate agreement (NDA) for verified partners.

What it is

UVS Detector is an SDR-based platform for hands-on radio-spectrum work in the field. The cycle is sweep (scan), detect, classify the modulation, identify the emitter, and where possible decode the payload. Everything is driven from a single operator-grade UI — 40+ panels and 4 layout presets (Default, Scanner, Decode, Deep dive) for different tasks, from a wide spectrum overview to a deep dive on a single signal.

Processing pipeline

• Sweep — configurable SweepPlans (Full / Targeted / Stare / FollowFHSS), stitched wide-band PSD, waterfall, heatmap, named band presets.
• Detect — noise-floor tracker, CA-CFAR, peak grouping, burst segmentation, hit aggregation, dedicated FHSS tracker, JSONL detection log.
• Classify — a feature stack (bandwidth, cumulants, α-SCF, cyclostationary features, chirp, fingerprint) and a fusion classifier that weighted-combines rules, a constellation EVM probe, and an ML model. 24 modulation classes.
• Identify — Bayesian fusion of frequency, modulation class, fingerprint and regional spectrum allocations (ITU r1/r2/r3 + national files) against a database of 339 emitters (236 civilian + 103 hostile). A separate layer — the hostile-intel overlay for RU tactical radio and EW, enabled in the appropriate operating modes.
• Decode — analog video (PAL B&W, PAL colour scaffold, NTSC), audio (NBFM/WFM/AM/SSB), digital protocols (FT8, WSPR, CW, DMR, LTE MIB, WiFi PHY, LoRa) and FPV digital; about 20 dissectors in the v1.0 ship set, plus a broader protocol catalogue (aviation, maritime, broadcast, GNSS, IoT) that comes online in tiers.

Classification and learning

The classifier is multi-stage: fast rules on signal statistics first, then a constellation-lock EVM probe for PSK/QAM, then an ML model (ONNX encoder + classifier). Results are merged by weighted fusion, so adding ML doesn’t break the deterministic rule behaviour.

The operator isn’t just a consumer of the verdict: a “Not X” correction button flags a wrong classification, and those labels are collected into a dataset for model retraining. The classifier backend is switchable in settings — globally or per drone family — so the system can be tuned to a specific theatre.

Direction finding

A coherent backend over paired AD9361 SDRs (E310 / LibreSDR / Pluto in any combination) sharing a 10 MHz reference and PPS. Supported algorithms — MUSIC, correlative interferometer, Watson-Watt and pseudo-doppler. The dual_coherent profile scales to 2–6 AD9361 devices. Additionally — a passive bistatic radar scaffold with an FM / DAB+ / DVB-T illuminator catalogue, and multi-station TDOA federation in LAN / Full modes for cross-station geolocation.

Hardened network architecture

Three deployment modes, chosen by the first-boot wizard:

• Isolated — full autonomy: no outbound connections; the whole RF pipeline, recording and playback stay local.
• LAN — sync within the local network only: TDOA federation and an S2S mTLS mesh between stations, nothing leaves the network.
• Full — full participation: station registry, shared signature database, integration API, auto-update, telemetry.

In-house PKI: soft-cert station identity with an AES-GCM keyring; operators authenticate via a PBKDF2 vault; revocation is an Ed25519-signed CRL with a kill-switch. Auto-update is a cohort-staged signed manifest with 2-attempt rollback and GPG-signed packages. Integration REST API with JWT and rate limiting (Full mode). The shared signature database is federated and anonymised — contributions are aggregated under a k-anonymity floor, with no raw IQ. Telemetry has 3-tier consent (off / pull-only / full). Storage — PBKDF2 + AES-GCM software sealer with a Linux TPM probe.

A separate component — the chain-of-custody session signer: a canonical-JSON session manifest signed with Ed25519. Captures can serve as evidence with a proper audit trail.

Field readiness

Target platform — Ubuntu 26.04 LTS amd64 (the sole production target after the 2026-04 narrowing). It ships as a .deb with a systemd unit and as a portable AppImage (backward-compatible to Ubuntu 24.04), both GPG-signed. It runs on a compact x86_64 station (mini-PC class) with a TPM for at-rest encryption; the SDR attaches over libiio (USB or IP). For the first minutes after launch, synthetic sources are available for a smoke test — the full interface works before any hardware is attached; then the SDR is connected and scanning begins.

How to get access

Builds, a demo and full technical documentation — by separate agreement; possession of the source or binaries by itself does not grant a licence. Reach out via the contact form: we’ll ask for a short brief on the use case, verify the counterparty, and agree NDA terms. The software is dual-use (export-controlled); defensive use by the UA Armed Forces and NATO partner forces is provided for separately in the EULA.