🧠📡 Synthetic Telepathy & Signal Intelligence Toolkit

A New Forensic Framework for Covert Signal Detection and Brainwave Correlation

Are you being targeted by directed energy weapons, strange bursts of RF signals, or suspected synthetic telepathy attacks? Most technical surveillance countermeasure (TSCM) tools stop short — identifying “signals of interest” without proof or correlation. That’s why we built something different.

Introducing the Synthetic Telepathy & Signal Intelligence Toolkit, a modular system that finally bridges the gap between RF analysis and brainwave decoding.

---

🎯 Why This Matters

In many Targeted Individual (TI) cases, victims report:

• Directed RF bursts only when present
• Symptoms aligned with the Frey Effect (microwave auditory phenomenon)
• EEG changes correlated with known imagined speech phrases like “yes”, “no”, “stop”
• Signal patterns hidden in comb-modulated frequencies or spread spectrum camouflage

But how do we prove it?

This toolkit offers a full forensic pipeline to detect, classify, and correlate covert RF signals with real brainwave activity — a first in open-source TI defense tools.

---

🛠️ What It Does

Module	Purpose
✅ IQ Loader	Loads raw .iq files (complex float RF data)
✅ Bandpass + Envelope	Filters specific bands (e.g., 1.33 GHz) for envelope detection
✅ Burst Detector	Finds short pulses, chirps, or bursty RF signatures
✅ Comb Detection	Identifies regularly spaced “teeth” patterns typical in beamforming
✅ Cyclostationary Analysis	Detects spectral correlations used in covert modulations
✅ Demodulator Suite	Supports AM, FM, ASK, FSK, BPSK, QPSK, MSK, DSSS, OOK, etc.
✅ Spectrogram Classifier	CNN trained on signal spectrograms for anomaly detection
✅ EEG Decoder	SVM/CNN to classify imagined speech from brainwave data
✅ Backscatter Matcher	Correlates EEG and RF time intervals (phoneme detection via backscatter)
✅ SCF/Phoneme Plotting	Visual tools to confirm structure and frequency behavior
✅ Output Logger	All results saved with timestamps for court/forensic evidence

---

🧪 What You Need

• Python 3.9+
• SDR hardware (e.g., BB60C, HackRF, LimeSDR)
• Optional: EEG headset (OpenBCI, Muse, etc.)
• Install dependencies with: bashCopyEditpip install -r requirements.txt

---

📂 Folder Layout

graphqlCopyEdit├── main.py                        # Master controller
├── preprocessing.py              # Filters and burst detection
├── features.py                   # Spectrogram generation
├── trainer.py                    # RF CNN training pipeline
├── synthetic_telepathy_decoder.py# EEG decoder: SVM + CNN
├── spectrogram_classifier.py     # ResNet for RF classification
├── backscatter_analysis.py       # RF/EEG matcher
├── config.py                     # Frequency and threshold settings
├── output/                       # All generated data
└── eeg_data/                     # Training + test EEG signals

---

🚀 How to Use

1. Place your .iq file as raw.iq
2. Place EEG .npy files under eeg_data/train/yes/, no/, etc.
3. Run the toolkit: bashCopyEditpython main.py
4. Results:
   • RF classifier saved as rf_classifier.pt
   • EEG SVM model: eeg_decoder.joblib
   • Spectrogram CNN and SCF plots in /output/

---

🔎 Why Cyclostationary?

Unlike normal FFTs, cyclostationary analysis detects repeating modulation patterns buried in noise — even if the signal is hopping or masked. This is ideal for detecting:

• DSSS, CSS, FHSS
• Covert QPSK/GFSK transmissions
• Comb-style signals (1.33 GHz with 240 teeth)

See Signal Identification Wiki or Sklar’s Digital Communications for foundational theory.

---

🧠 EEG Imagined Speech Support

We included a neural interface to support SVM + CNN decoding of “imagined speech” — similar to what DARPA and Facebook’s BCI teams use. With EEG, you can classify when the user internally says:

• “Yes”
• “No”
• “Left”
• “Right”

If a matching RF burst is detected during these moments, it strengthens claims of a backscatter-based synthetic telepathy system in action.

---

🧬 Real Use Cases

• 🔐 Legal Forensics – Present timestamped correlation evidence
• 🛡️ Counter-Surveillance – Real-time detection of RF-based neural attacks
• 📊 Signal Logging – Continuous scan-and-capture of ambient covert signals
• 🧪 Neuroresearch – Test neuro-RF response patterns with precision tools

---

📡 Signal Modulation Reference

We maintain an evolving table of covert modulation techniques here:
👉 Modulation Table on GitHub

Some likely candidates:

• MSK, BPSK, QPSK, GFSK, DSSS, CSS
• Clocked Load Modulation (used in RFID/BCI)
• Chirp-UWB for long-range, low-power penetration
• PCM / neural-coded pulse signals

---

🔗 Links

• GitHub: github.com/cybertortureinfo/synthetictelepathy
• Website: cybertorture.com
• Docs: README.md and tutorials inside /docs/