How ethos-lab/biosignal-auth-harmful works
This repository supports biosignal-spoofing research: shared dataset loading and processing feed CycleGAN-style signal generation, while a collection of ECG, PPG, BCG, and SCG authentication implementations evaluates original and spoofed signals. The principal workflow is configure/load paired biosignals, train a translator, then prepare or segment authentication data, train or load an identity model, and evaluate spoof acceptance. Edges reflect README statements and shown source references; several authentication implementations are represented by their directory because their runtime wiring was not sampled.
Main entry points: datasets.py Dataset access · train_contrastive_cardiogan.py Translator training · EDITH EDITH authentication · datasets Dataset adapters
Components 30
Shared data
- Dataset access
custom_datasets/custom_datasets/datasets.py - Dataset properties
custom_datasets/custom_datasets/properties.py - Signal processing
custom_datasets/custom_datasets/processing.py
Spoof generation
- Paired datasets
model_training/datasets/base_dual_dataset.py - Dataset metadata
model_training/datasets/dataset_metadata.py - Training data utilities
model_training/datasets/dataset_utils.py - Dataset adapters
model_training/datasets - Translator training
model_training/train_contrastive_cardiogan.py - Generator networks
model_training/models/yhcardiogan.py - Training losses
model_training/losses.py - Generation utilities
model_training/utils.py
ECG authentication
- DeepECG preparation
authentication_systems/ECG/DeepECG/dataset.py - DeepECG signals
authentication_systems/ECG/DeepECG/signal_processing.py - DeepECG authentication
authentication_systems/ECG/DeepECG - ECGXtractor preparation
authentication_systems/ECG/ECGXtractor/src/prepare_dataset.py - ECGXtractor loader
authentication_systems/ECG/ECGXtractor/src/loader.py - Siamese network
authentication_systems/ECG/ECGXtractor/src/network_authentication_siamese_CNN.py - ECGXtractor runtime
authentication_systems/ECG/ECGXtractor/src/util.py - EDITH segmentation
authentication_systems/ECG/EDITH/segment_signals.py - EDITH models
authentication_systems/ECG/EDITH/torchmodels.py - EDITH training utilities
authentication_systems/ECG/EDITH/train_utils.py - EDITH authentication
authentication_systems/ECG/EDITH - KeyToYourHeart
authentication_systems/ECG/KeyToYourHeart
Other authentication
- CorNET data
authentication_systems/PPG/CorNet/datasets.py - CorNET model
authentication_systems/PPG/CorNet/model.py - CorNET training and evaluation
authentication_systems/PPG/CorNet - Hwang2020 authentication
authentication_systems/PPG/Hwang2020 - BCG authentication
authentication_systems/BCG - SCG authentication
authentication_systems/SCG
Other components
- Researcher
Connections 37
- Researcher → Dataset access: requests signals
- Dataset access → Dataset properties: reads configuration
custom_datasets/custom_datasets/datasets.py - Dataset access → Signal processing: uses processing
custom_datasets/custom_datasets/datasets.py - Paired datasets → Dataset metadata: uses metadata
model_training/datasets/base_dual_dataset.py - Dataset adapters → Paired datasets: extends dataset
model_training/datasets/ecgppg_dalia.py - Dataset adapters → Training data utilities: uses utilities
model_training/datasets/ecgppg_dalia.py - Dataset adapters → Dataset access: loads raw pairs
model_training/datasets/ecgppg_dalia.py - Researcher → Translator training: starts training
- Translator training → Dataset adapters: loads batches
model_training/train_contrastive_cardiogan.py - Translator training → Generator networks: builds networks
model_training/train_contrastive_cardiogan.py - Translator training → Training losses: selects losses
model_training/train_contrastive_cardiogan.py - Translator training → Generation utilities: uses utilities
model_training/train_contrastive_cardiogan.py - Researcher → ECGXtractor preparation: prepares evaluation data
- ECGXtractor preparation → Dataset access: loads signals
- ECGXtractor runtime → ECGXtractor loader: uses loader
authentication_systems/ECG/ECGXtractor/src/util.py - ECGXtractor runtime → Siamese network: uses network
authentication_systems/ECG/ECGXtractor/src/util.py - Siamese network → ECGXtractor runtime: compiles through
authentication_systems/ECG/ECGXtractor/src/network_authentication_siamese_CNN.py - DeepECG preparation → Dataset access: loads signals
authentication_systems/ECG/DeepECG/dataset.py - DeepECG preparation → DeepECG signals: processes signals
authentication_systems/ECG/DeepECG/dataset.py - EDITH authentication → Dataset access: loads signals
authentication_systems/ECG/EDITH/train_siamese.py - EDITH authentication → EDITH segmentation: segments signals
authentication_systems/ECG/EDITH/train_siamese.py - EDITH authentication → EDITH models: uses models
authentication_systems/ECG/EDITH/train_siamese.py - EDITH authentication → EDITH training utilities: uses utilities
authentication_systems/ECG/EDITH/train_siamese.py - CorNET training and evaluation → CorNET data: prepares data
authentication_systems/PPG/CorNet/eval.py - CorNET training and evaluation → CorNET model: evaluates model
authentication_systems/PPG/CorNet/eval.py - Hwang2020 authentication → Dataset access: loads signals
authentication_systems/PPG/Hwang2020/eval.py - Hwang2020 authentication → Signal processing: uses processing
authentication_systems/PPG/Hwang2020/eval.py - BCG authentication → Dataset access: loads signals
authentication_systems/BCG/ZhangRNN/eval.py - SCG authentication → Dataset access: loads signals
authentication_systems/SCG/MotionArtifactResilient/eval.py - SCG authentication → Signal processing: uses processing
authentication_systems/SCG/HsuWaveletTransform/train_and_eval.py - Researcher → DeepECG authentication: trains and evaluates
- Researcher → EDITH authentication: trains and evaluates
- Researcher → KeyToYourHeart: trains and evaluates
- Researcher → CorNET training and evaluation: trains and evaluates
- Researcher → Hwang2020 authentication: evaluates
- Researcher → BCG authentication: evaluates
- Researcher → SCG authentication: evaluates