Guanyu-Lin/FedAV

Cyberattack vulnerability and resilience of cooperative driving automation using federated learning

This is our Pytorch implementation for the paper:

Cyberattack vulnerability and resilience of cooperative driving automation using federated learning.

Data Downloading

The original data can be downloaded at: https://data.transportation.gov/Automobiles/Test-Data-of-Proof-of-Concept-Vehicle-Platooning-B/wpek-zziu

Data Pre-processing

The script is Mxied_Cyberattack_Simulation/PreprocessAndAttack.sh which can be excuted via:

bash Mixed_Cyberattack_Simulation/PreprocessAndAttack.sh

Federated Model Training

To train our model on simulated dataset (with hyper-parameter searching):

python server.py

Federated Model Inference

To inference our models on simulated dataset (with hyper-parameter searching):

python server_inference.py

Baseline Model Training

To train baseline models on simulated dataset (with hyper-parameter searching):

python baseline.py

Baseline Model Inference

To inference baselines models on simulated dataset (with hyper-parameter searching):

python baseline_inference.py