Master's thesis: Explainable AI for Intrusion Detection System in Automotive Ethernet

We are inviting a motivated master’s student to collaborate with us at the Industrial Systems Department at RISE under the INTERSTICE project. Our research is dedicated to developing advanced security solutions for automotive networks, with a strong focus on collaborative projects with Swedish industrial and academic partners.

Background and Purpose
With the increasing integration of Ethernet-based networks in automotive 
systems, the complexity and potential vulnerability to cyber threats also escalate. The application of Artificial Intelligence (AI) in Intrusion Detection Systems (IDS) offers promising avenues for detecting and mitigating such threats. However, the black-box nature of many AI approaches poses challenges in terms of trustworthiness and reliability. Explainable AI (XAI) seeks to make AI decisions in IDS more transparent 
and understandable, which is crucial for their acceptance and implementation in safety-critical automotive environments.

Thesis Description
The goal of this thesis is to develop an explainable AI (XAI) model that can provide not 
only high accuracy in detecting intrusions in Automotive Ethernet but also clear insights into the decisionmaking processes of the model. The thesis will involve the exploration and implementation of advanced XAI techniques within an automotive Ethernet IDS framework. 

You will design and test various models to highlight the trade-offs between explainability, performance, and computational efficiency. Additionally, the thesis will examine the impact of different types of attacks on the model’s explanatory power. Key tasks include:

1. Review of explainable AI, focusing on its critical role in enhancing the security and trustworthiness of cybersecurity systems
2. Study of intrusion detection in Automotive Ethernet using the algorithms and datasets provided at the start of your research
3. Data preparation and investigation of advanced methodologies and tools for Explainable AI, noting their applicability and limitations in Automotive Ethernet IDS
4. Evaluation of how the integration of XAI affects the performance, reliability, and trustworthiness of intrusion detection systems in Automotive Ethernet environments.

This work will be carried out in close collaboration with the Swedish automotive industry.

Duration: 6 months of full-time engagement. 
Application Deadline: November 15th, 2024. 
Start Date: By January 2025. 
Scope: 30 hp.
Location: RISE Industrial Systems, Sundsvall. Flexibility to work partly remotely

Who Are You?
The ideal candidate will have basic knowledge in computer science and cybersecurity, with 
specific skills in machine learning. Proficiency in programming languages such as Python and machine learning frameworks (e.g., TensorFlow, PyTorch), and a keen interest in network security and ethical AI are expected. 

Welcome with your application!
To know more, please contact Nishat Mowla (nishat.mowla@ri.se, tel 073 051 19 37). Applications should include a brief personal letter, CV/resume, recent transcript of records, and a code example written by you. Candidates are encouraged to send in their application as soon as possible but at the latest by the 15th of November 2024. Suitable applicants will be interviewed as soon as applications are received.

Keywords: Master thesis, Automotive Ethernet, Intrusion Detection Systems, Explainable AI, RISE