ainfosec/FISSURE

What is FISSURE?

FISSURE ("Frequency Independent SDR‑based Signal Understanding and Reverse Engineering") is an open‑source software framework for working with radio‑frequency (RF) signals using software‑defined radios (SDRs). It bundles together a GUI dashboard, a set of reusable plugins, and a workflow engine that lets users detect, classify, record, replay, and manipulate raw IQ data, then discover protocols, craft packets, fuzz them, and test for vulnerabilities. The system can run on a single laptop or be scaled out to many distributed sensor nodes that talk to each other over IP or long‑range radio links.

Who might use it?

• Field operators – need a quick‑to‑deploy toolkit for spotting unknown RF emitters, geolocating them, and feeding alerts into tactical situational‑awareness apps like WinTAK/ATAK.
• Researchers & educators – want a common platform for experimenting with SDR signal processing, testing new machine‑learning models, or teaching RF reverse‑engineering without having to stitch together dozens of separate tools.
• Hobbyists & students – can explore SDR workflows, build datasets, and try out protocol‑fuzzing on inexpensive hardware.

Core capabilities (as described in the README)

Capability	What it means
Signal detection & classification	Scan the spectrum, spot active signals and label them (e.g., Wi‑Fi, Bluetooth, custom protocols).
IQ capture, replay & manipulation	Save raw complex samples, replay them later, or apply transformations (frequency shift, filtering, etc.).
Protocol discovery & packet crafting	Use built‑in libraries or custom plugins to decode unknown protocols and generate custom packets.
Fuzzing & vulnerability testing	Automatically mutate packets and send them to a target to find weaknesses.
Archiving & playlists	Store captured signals in a searchable library and create playlists for regression testing.
Distributed sensor coordination	Manage multiple SDR nodes, synchronize captures, and share data across a network.
Geolocation & direction finding	Combine measurements from several nodes to triangulate emitter locations.
TAK integration	Push detections, alerts, and target data into WinTAK/ATAK maps for real‑time situational awareness.
AI/ML automation	Hooks exist for plugging in machine‑learning models to automate parts of the workflow (e.g., classification).

Architecture at a glance

• Dashboard (desktop GUI) – visual front‑end for configuring nodes, viewing spectra, and launching plugins.
• Headless sensor nodes – can run on small computers (Raspberry Pi, ruggedized boxes) and be controlled remotely.
• Container support – the whole stack can be packaged in Apptainer (formerly Singularity) containers for reproducible installs.
• Plugin & Action framework – capabilities are packaged as plugins that can be executed on the dashboard, on a node, or from within WinTAK/ATAK.
• Fracture – a commercial‑grade, hardware‑focused deployment that builds on FISSURE’s software, adding rugged enclosures, networking, and mission‑specific extensions.

Getting started (from the README)

1. Choose a branch – the active Python3 branch supports PyQt5 and GNU Radio 3.8/3.10. An older Python2_maint-3.7 branch exists only for legacy GNU Radio 3.7 needs.
2. Install – follow the installation guide on the Read‑the‑Docs site (links provided in the README). Options include a native install, an Apptainer container, or a pre‑built installer.
3. Connect hardware – supported SDRs include USRP series, HackRF, RTL‑SDR, LimeSDR, bladeRF, PlutoSDR, SDRplay, and generic 802.11 adapters.
4. Launch the dashboard – configure one or more sensor nodes, start a detection scan, and explore the built‑in plugins.
5. Extend – write your own plugin or action (e.g., a custom ML classifier) and drop it into the plugin folder; it becomes available across the whole system.

Why it matters

FISSURE tries to solve a common pain point in the RF security community: the fragmentation of tools. Instead of juggling separate scripts for capture, analysis, fuzzing, and reporting, users get a unified environment that can be run on a laptop in a lab or deployed across a fleet of tactical radios in the field. Its open‑source nature also makes it a useful teaching platform and a base for research projects that need to integrate AI/ML models with live RF data.

---

Sources: All details above are taken directly from the repository’s README (overview, capabilities, deployment options, hardware list, and getting‑started notes).