30 hp - Edge-Deployable Machine Learning-Driven Distributed Intrusion Detection for In-Vehicle CAN C

Background:
Scania is one of the world’s leading manufacturer of trucks and buses for heavy transports, as well as industrial and marine engines. Transport services and logistics services make up an increasing part of our business, which guarantees Scania’s customers cost-efficient transport solutions and high availability. Over a million Scania vehicles are in active use, in over 100 countries.
In the Connected Systems department within Scania R&D, we develop innovative solutions for connected vehicles, driving Scania's transition toward a sustainable transport system. Advanced data analytics is a pivotal enabler in this transformation and Scania’s research background, combined with its in-house expertise in machine learning-driven analysis of vehicle data, positions us at the forefront of this development.

Target/scope:
Ensuring cyber security requirements for connected vehicles is vital to safeguard the safety, functionality, and reliability of vehicles. As the automotive industry continues to evolve, cybersecurity will remain a cornerstone and pose disruptive challenges. International regulations such as UN Regulation No 155, necessitate cyber security measures to detect and prevent cyber-attacks against vehicles, as well as support the monitoring capability for detecting threats and vulnerabilities. Onboard intrusion detection systems (IDS) for in-vehicle communication networks can help detect various cyber attacks including sensor-initiated, infotainment-initiated, telematics-initiated, and direct interface-initiated attacks with different disturbing mechanisms such as fabrication (e.g., denial of service, fuzzy, and replay attacks), suspension, and masquerade (e.g, spoofing attack). Network IDS provides a layer of security by monitoring and analyzing the data traffic, and identifying suspicious activities that could indicate an intrusion. It facilitates the timely detection of anomalies, enabling the application of appropriate mitigation measures and ensuring compliance with the regulations.

This project outlines a research work to explore and apply a distributed machine learning-driven IDS to create a scalable, collaborative IDS solution. The goal is to minimize onboard resource usage by utilizing lightweight IDS models and ensure scalability while effectively detecting anomalies in the in-vehicle CAN communication environment.  

Description of the assignment:
-    Explore distributed learning methods for intrusion detection on automotive networks.
-    Analyze the CAN data (normal behavior and attack-representing data, e.g., denial of service, fuzzy, replay, and spoofing attacks) to identify intrusion patterns.
-    Develop anomaly detection models in a distributed manner across multiple nodes and develop a conceptual framework for demonstrating a distributed solution to in-vehicle ML network IDS.
-    Performance Benchmarking: assess the system’s detection capabilities and resource usage in distributed settings. 

Education/line/direction
Assign education, line or direction: masters programmes in Machine Learning, Software Engineering, Data Science, Computer Science/Engineering, Mathematics, or similar.

Number of students: 1-2 (pairs are preferred but not a requirement, if so, refer to each other in the personal letter)
Start date for the Thesis project: January 2025
Estimated timescale: 20 weeks

Contact person and supervisor:
Mahshid Helali Moghadam, data scientist, 08-553 826 54, mahshid.helali.moghadam@scania.com 
Juan Carlos Andresen, group manager, 08-553 835 16, juan-carlos.andresen@scania.com 

Application:
Your application should contain CV, personal letter, and copies of grades

Date of publication:
Until 2024-10-31. Applicants will be assessed on a continuous basis until the position is filled. 

A background check might be conducted for this position. We are conducting interviews continuously and may close the recruitment earlier than the date specified.  

Thesis Worker