Military-Grade 2.5D/3D Wi-Fi Spatial Mapping, Signals Intelligence (SIGINT), and Bayesian Localization Engine.
Standard Wi-Fi analyzers are mathematically blind. They rely on chaotic Received Signal Strength (RSSI) tied to a flat 2D GPS pin. They fail the moment a surveyor turns their body, walks past a concrete wall, or travels down a straight hallway. Multipath fading, torso eclipsing, and collinear ambiguity render traditional tools useless for exact physical localization.
Wolf Mark does not guess. It operates at the Layer 1 API boundary, ingesting raw RF telemetry and running it through a custom wave-propagation physics simulator. By fusing asymmetric Kalman filtering, Principal Component Analysis (PCA), and asynchronous dual-stream GPS polling, Wolf Mark translates invisible radio waves into high-resolution probabilistic heatmaps.
RSSI is a fallback; the speed of light is absolute. When available, Wolf Mark intercepts hardware-level is80211mcResponder packets and constructs direct Round Trip Time (RTT) requests. By measuring the nanosecond physical travel time of the wave, it injects an astronomical weight multiplier (109) into the Bayesian grid—instantly overpowering probabilistic math with raw physics.
Multipath fading is mathematically hostile. Wolf Mark tames the spectrum using a customized 1D Kalman Filter. If a signal drops by >10 dBm while moving less than 3 meters, the engine assumes a "Torso Eclipse." It balloons the measurement noise multiplier (5.0x) and rejects the anomaly to preserve matrix integrity.
Instead of assuming a static 20 dBm transmit power, Wolf Mark dynamically scales baseline origin power (P₀) across the RF spectrum (12dBm for 6GHz, 15dBm for 2.4GHz, 18dBm for 5GHz). It actively adjusts the Path Loss Exponent (n) from 2.2 to 3.8 to mathematically model concrete wall absorption in real-time.
Wolf Mark runs two distinct computational engines, allowing the operator to scale CPU allocation based on mission parameters.
Designed to map thousands of background APs simultaneously without melting the UI thread. It executes coarse-to-fine spatial grid sweeps (±120m → ±6m).
Crucially, it implements True 3D Math, utilizing the operator's live GPS altitude (Z-axis) to calculate the 3D spatial hypotenuse—preventing vertical high-rise infrastructure from skewing horizontal coordinates.
Sacrifices device battery to dedicate 100% of CPU cycles to hunting a single target MAC address.
If you walk perfectly down a long hallway, standard trilateration creates two identical probabilities (one on your left, one on your right). Wolf Mark monitors your GPS path using a Covariance Matrix and Principal Component Analysis (PCA).
If the extracted Eigenvalues trigger a major/minor axis ratio > 25.0, the system flags a Collinear Ambiguity. It dynamically flattens the probability curve, rendering a "mirrored cloud" on your HUD to prompt you to walk perpendicularly and "collapse the wave function."
Standard map SDKs limit vector rendering. Wolf Mark throws them out. The UI is a raw Compose Canvas mathematically glued to the satellite layer using deep screen-density calculus:
This guarantees mathematically perfect 1-to-1 vector overlay tracking during complex pinches, pans, and live compass rotations.
Share your network intelligence, not your physical address. Wolf Mark is built to feed external Machine Learning and AI models without compromising Operational Security (OPSEC).
Because longitude physical distance shrinks near the poles, arbitrarily shifting map coordinates warps spatial geometry.
Wolf Mark calculates a strict boundary limit guaranteeing ≤ 0.5% spatial distortion. It spins the Longitude 0→360°, shifts the Latitude within the strict distortion bound, and randomly flips the dataset across hemispheres. You get a perfectly preserved topological dataset for AI analysis, irreversibly decoupled from your real-world location.
Export literal un-culled RF histories, n-values, P₀ Tx powers, Time-of-Flight vectors, and exact Pre-Softmax 61x61 Likelihood Matrices directly to structured JSON. Feed the raw physical physics data directly into Python, TensorFlow, or corporate SIEMs.
{
"device": "Google Pixel",
"obfuscated": true,
"mac": "8f2a9c...",
"gridMaxLikelihood": -12.45,
"observations": [
{"lat": -34.12, "lng": 151.29, "rssi": -42,
"weight": 31.62, "n": 2.2, "p0": 15.0}
]
}Physical Penetration Testers (Red Teams): Locate hidden rogue Access Points, evil twins, and unauthorized shadow-IT hardware within enterprise buildings with room-level precision.
Network Architects: Map out 5GHz/6GHz signal propagation, concrete wall degradation, and true physical coverage gaps.
Cybersecurity Analysts & Data Scientists: Export raw Layer 1 RF telemetry to external Large Language Models (like Gemini Deep Think) for deep temporal analysis.