Platform capabilities, architecture, API references, and operational documentation for the Varta Anti-Drone Platform.
Each feature is marked by tier availability. Full = complete capability, Basic = limited subset, Node = contributes data, Hub = aggregates data, Receive = receives fleet updates, Admin = manages fleet updates.
| Feature | Mini v1 | Mini v2 | Pro | Max |
|---|---|---|---|---|
| Detection & Classification | ||||
| Multi-Band RF Monitoring | Full (freq/power) | Full (I/Q, dual RX) | Full (I/Q analysis) | Full (I/Q + fusion) |
| RF Signature Database | Basic (10 generic bands) | Full (43+ IDs) | Full (43+ IDs) | Full (43+ fused) |
| 5-Path Jammer Detection | Full | Full | Full | Full |
| Baseline Anomaly Detection | Full | Full | Full | Full |
| Multi-Band Correlation | Basic (power only) | Full (mod + power) | Full (mod + power) | Full (+ multi-sensor) |
| Temporal Pattern Analysis | Basic (approach) | Full | Full (attack prediction) | Full (+ fleet-wide) |
| AI/ML & Advanced Analysis | ||||
| Cyclostationary Analysis | — | Full | Full | Full |
| FHSS Hop Pattern Analysis | — | Full | Full | Full |
| Modulation Classification | — | Full | Full | Full |
| Bandwidth Discrimination | — | Full | Full | Full |
| CNN Spectrogram Classifier | — | Full (ONNX CPU) | Full (ResNet-18, 90.3%) | Full (TensorRT INT8) |
| RF Gate Classifier (4 datasets) | — | Full | Full | Full |
| Benign Signal Rejection | — | Full (protocol preamble correlators) | Full (WiFi STS, BLE access, LoRa CSS) | Full |
| Hybrid ML Decision Engine | — | Full (4 strategies) | Full (4 strategies) | Full (4 strategies) |
| Flight Mode Inference | — | Full | Full | Full |
| Multi-Sensor & Geolocation | ||||
| Multi-Sensor Data Fusion | Node | Node | Node | Hub |
| TDOA Geolocation | — | — | — | Full (3+ sensors) |
| Phase Interferometry DF | — | — | Full (DF stations) | Hub (fusion) |
| DF Bearing Intersection | — | — | Node (bearing) | Hub (intersection) |
| DF+RSSI Hybrid | — | — | Node (bearing) | Hub (hybrid) |
| RSSI Triangulation | — | — | — | Full (2+ sensors) |
| Radar Fusion | — | — | — | Full (API ingest) |
| Swarm Detection | — | — | — | Full |
| NATO MGRS Grid References | — | — | — | Full |
| Intelligence & Compliance | ||||
| FAA RemoteID Correlation | Basic (BLE) | Basic (BLE) | Full (BLE + WiFi bridge) | Full (fleet aggregate) |
| Protected Zone Management | — | — | — | Full |
| DJI DroneID / OcuSync Decode | — | Full (I/Q decode) | Full (I/Q decode) | Full (map enrichment) |
| STIX/TAXII 2.1 Export | — | — | — | Full |
| Acoustic Detection (ML) | Full (USB mic) | Full (USB mic, 88.9%) | Full (USB mic, 88.9%) | Full (enriched) |
| Forensic I/Q Capture | — | Full (auto capture) | Full (auto capture) | Full (auto capture) |
| Field Capture Sync | — | Full (upload to Max) | Full (upload to Max) | Full (inbox + analysis API) |
| Historical Threat Browsing | — | — | — | Full (CSV) |
| Fleet Management & Operations | ||||
| Sensor Health Intelligence | Basic (local) | Basic (local) | Basic (local + MQTT) | Full (dashboard) |
| Sensor Lifecycle Management | — | — | — | Full (25+ states) |
| Sensor Pairing & Auth | — | — | — | Full (bcrypt + HMAC) |
| Sensor Decommission Blocklist | — | — | — | Full |
| Rapid Signature Pipeline | — | Basic (capture) | Basic (capture) | Full (capture → review → deploy) |
| Signature Registry OTA | Receive | Receive | Receive | Admin + Mirror |
| Tactical Web Dashboard | — | — | — | Full |
| Security & Safety | ||||
| Signed Config Verification | Full | Full | Full | Full |
| TLS 1.3 + mTLS Transport | Full | Full | Full | Full |
| SQLCipher Edge Storage | Full | Full | Full | — (TimescaleDB) |
| Detection Provenance | Full | Full | Full | Full |
| Never-CLEAR Safety Rule | Invalid sensor data always returns SENSOR_FAILURE, never CLEAR | |||
Read deep-dive documentation for 18 flagship platform capabilities →
Language: Python 3.10+
Signal Processing: NumPy, SciPy
Detection: Cyclostationary, FHSS, RF Gate, Benign Rejector
ML: PyTorch (training), ONNX Runtime (Mini v2), TensorRT INT8 (Pro/Max)
SDR Hardware: Fish Ball SDR ($99, GigE) primary; PlutoSDR, HAMGEEK AD9361 also supported
API Framework: FastAPI (REST + WebSocket)
Internal Transport: gRPC
Edge DB: SQLite + SQLCipher (AES-256-CBC)
Max DB: TimescaleDB (PostgreSQL hypertable)
Capture Sync: Edge upload pipeline + Max analysis APIs
Monitoring: Prometheus + Grafana
Sensor Bus: MQTT via Mosquitto (TLS 1.3, mTLS)
Command Channel: ZeroMQ (CURVE encryption)
Streaming: gRPC (detections, health, alerts)
Real-time UI: WebSocket
Visual decision flow diagrams showing how Varta processes signals through the multi-tier detection pipeline.
Four tiers with increasing capability: Mini v1 (frequency/power), Mini v2 (full I/Q + ONNX), Pro (full I/Q + TensorRT), Max (multi-sensor fusion).
graph TB
subgraph MiniV1["Varta Mini v1 - TinySA"]
M1[TinySA Spectrum Scan]
M2[Frequency + Power Only]
M3[Jammer Heuristic]
M4[Generic Band Classification]
M5[10 Generic Bands]
M1 --> M2 --> M3 --> M4 --> M5
end
subgraph MiniV2["Varta Mini v2 - HAMGEEK + Pi 5"]
V1[Dual-RX I/Q Capture]
V2[35-Field Feature Extraction]
V3[NoiseGate + RFGate + BenignReject]
V4[CNN ONNX on CPU]
V5[Hybrid ML Decision]
V6[43+ Specific Signatures]
V1 --> V2 --> V3 --> V4 --> V5 --> V6
end
subgraph Pro["Varta Pro - Fish Ball / PlutoSDR + Jetson"]
P1[Fish Ball/PlutoSDR I/Q Capture]
P2[35-Field Feature Extraction]
P3[NoiseGate + RFGate + BenignReject]
P4[Cyclostationary + FHSS + Modulation]
P5[CNN TensorRT on GPU]
P6[Hybrid ML Decision]
P7[43+ Specific Signatures]
P1 --> P2 --> P3 --> P4 --> P5 --> P6 --> P7
end
subgraph Max["Varta Max - Command Center"]
X1[Multiple Sensor Inputs]
X2[Health-Gated Fusion]
X3[Calibration Normalization]
X4[Multi-Band Correlation]
X5[TDOA/DF/RSSI/Radar Triangulation]
X6[DroneID + MGRS Enrichment]
X7[Fused Detection + Position]
X1 --> X2 --> X3 --> X4 --> X5 --> X6 --> X7
end
MiniV1 -.MQTT.-> Max
MiniV2 -.MQTT.-> Max
Pro -.MQTT.-> Max
style MiniV1 fill:#1a3a5c,stroke:#4a9eff,stroke-width:2px
style MiniV2 fill:#21537a,stroke:#5fb3ff,stroke-width:2px
style Pro fill:#1a4a2c,stroke:#4aff4a,stroke-width:2px
style Max fill:#4a3a1a,stroke:#ffaa4a,stroke-width:2px
Multiple drone types operate in the same frequency bands. Varta solves this with multi-factor heuristics combining frequency, bandwidth, modulation, hop patterns, and multi-band correlation.
graph TD
A[2.4 GHz ISM Band] --> B[DJI OcuSync]
A --> C[ELRS 2.4 GHz]
A --> D[TBS Tracer]
A --> E[WiFi Drones]
A --> F[Consumer FPV]
A --> G[Wideband Jammer]
H[900 MHz Band] --> I[Lancet Control]
H --> J[Orlan-10 Control]
H --> K[Supercam Control]
H --> L[ELRS 868/915]
H --> M[Crossfire 868/915]
H --> N[Shahed RFD900x]
style A fill:#f96,stroke:#333,stroke-width:2px
style H fill:#f96,stroke:#333,stroke-width:2px
How Varta separates 6+ overlapping systems in the 850-1020 MHz band.
flowchart TD
Start[900 MHz Signal] --> DualBand{Dual-band detected? 868-870 + 902-928 MHz}
DualBand -->|Yes| Lancet[LANCET confidence 0.85]
DualBand -->|No| Mod[Modulation Analysis]
Mod --> LoRa{LoRa CSS?}
LoRa -->|Yes| HopRate{Hop Rate?}
HopRate -->|40-60 Hz| LancetSingle[LANCET confidence 0.75]
HopRate -->|25-500 Hz| ELRS[ELRS confidence 0.75]
HopRate -->|~50 Hz| Crossfire[CROSSFIRE confidence 0.75]
LoRa -->|No| FHSS{FHSS Pattern?}
FHSS -->|Yes| HopSpeed{Hop Speed?}
HopSpeed -->|1-2 Hz| Orlan[ORLAN-10 confidence 0.70]
HopSpeed -->|~20 Hz| RFD900x[RFD900x Shahed confidence 0.60]
FHSS -->|No| Power{Power Level?}
Power -->|> -50 dBm| MilGeneric[MILITARY_UHF confidence 0.50]
Power -->|< -50 dBm| D900[DRONE_900 confidence 0.40]
style Lancet fill:#f33,stroke:#333,stroke-width:3px,color:#fff
style LancetSingle fill:#f66,stroke:#333,stroke-width:2px
style Orlan fill:#f96,stroke:#333,stroke-width:2px
style ELRS fill:#9cf,stroke:#333,stroke-width:2px
style Crossfire fill:#9cf,stroke:#333,stroke-width:2px
5-path jammer detection ensures no electronic warfare technique evades classification.
flowchart TD
Start[2.4 GHz Elevated Power] --> Occupancy{Wideband Occupancy >30% bins elevated?}
Occupancy -->|Yes| FlatnessCheck{Power Flatness Peak-avg < 6 dB?}
FlatnessCheck -->|Yes| WidebandJam[WIDEBAND JAMMING]
FlatnessCheck -->|No| BW{Bandwidth?}
BW -->|> 30 MHz| PossibleJam[Possible wideband]
BW -->|< 30 MHz| Drone[Likely drone signal]
Occupancy -->|No| Narrow{Narrow peak >30 dB above avg?}
Narrow -->|Yes| SpotJam[SPOT JAMMING]
Narrow -->|No| Signal[Analyze as signal]
Signal --> ModCheck{Modulation detected?}
ModCheck -->|Yes| DJI[Drone Confirmed]
ModCheck -->|No| Temporal{Temporal stability?}
Temporal -->|Stable| Drone2[Likely drone]
Temporal -->|Swept/bursts| Jammer2[Likely jammer]
PossibleJam --> MultiBand{Other bands active?}
MultiBand -->|Yes 5.8 GHz| DJIVideo[DJI with video - NOT jammer]
MultiBand -->|No| WidebandJam2[WIDEBAND JAMMING confirmed]
style WidebandJam fill:#f33,stroke:#333,stroke-width:3px,color:#fff
style SpotJam fill:#f33,stroke:#333,stroke-width:3px,color:#fff
style WidebandJam2 fill:#f33,stroke:#333,stroke-width:3px,color:#fff
style DJI fill:#9cf,stroke:#333,stroke-width:2px
style DJIVideo fill:#9f9,stroke:#333,stroke-width:2px
Multi-factor scoring: frequency (0.35), modulation (0.25), bandwidth (0.20), hop rate (0.15), symbol rate (0.05), with bonuses for cyclostationary and multi-band correlation.
flowchart TD
Start([Signal Features]) --> FreqScore[Frequency Match 0.35]
Start --> BWScore[Bandwidth Match 0.20]
Start --> ModScore[Modulation Match 0.25]
Start --> HopScore[Hop Rate Match 0.15]
Start --> SymScore[Symbol Rate Match 0.05]
Start --> CycloScore[Cyclostationary Bonus +0.15]
Start --> MultiBandScore[Multi-Band Bonus +0.25]
FreqScore --> Weights[Weighted Sum]
BWScore --> Weights
ModScore --> Weights
HopScore --> Weights
SymScore --> Weights
Weights --> BaseConf[Base Confidence]
BaseConf --> Bonuses[Add Bonuses]
CycloScore --> Bonuses
MultiBandScore --> Bonuses
Bonuses --> SNRGate{SNR < 10 dB?}
SNRGate -->|Yes| Cap35[Cap at 0.35]
SNRGate -->|No| Final[Final Confidence]
Cap35 --> Clamp[Clamp 0.0-1.0]
Final --> Clamp
Clamp --> Output([Confidence Score])
style Output fill:#9f9,stroke:#333,stroke-width:2px
View full architecture documentation with all decision flows →
Detailed documentation for 18 flagship capabilities with tier availability notes.
Decision flows, fusion logic, safety gates, and security controls.
REST, WebSocket, and MQTT interfaces for sensors and command center.
Signature catalog, bands, and threat categorization across platforms.
Interactive command center UI with simulated threats.
Platform milestones, field testing, and beta feature refinement.