Thesis Work – Federated Learning for Unsupervised Intrusion Detection, In-Vehicle CAN Network
Scania Group
full-time
Posted on:
Location Type: Hybrid
Location: Södertälje • 🇸🇪 Sweden
Visit company websiteJob Level
Mid-LevelSenior
Tech Stack
PythonPyTorchTensorflow
About the role
- Develop and train unsupervised VAE-based anomaly detection models to learn normal CAN behavior locally.
- Implement and evaluate distributed learning strategies such as FedAvg, FedPer, and FedProx.
- Compare federated vs. centralized training in terms of detection performance, model convergence, and communication overhead.
Requirements
- Solid understanding of neural networks, autoencoders, and unsupervised learning.
- Knowledge of deep learning frameworks (e.g., PyTorch or TensorFlow).
- Programming experience in Python.
- Experience with federated learning frameworks (e.g., FEDn, Flower).
- Familiarity with automotive network data (CAN) and cyber-attack scenarios.
Benefits
- Your application should contain the following: CV.
- Personal letter.
- Copies of grades.
- Optional: To propose a tentative approach to the problem.
Applicant Tracking System Keywords
Tip: use these terms in your resume and cover letter to boost ATS matches.
Hard skills
unsupervised learningneural networksautoencodersdeep learningPythonfederated learningVAE-based anomaly detectiondistributed learning strategiesmodel convergencedetection performance