Explainable AI (XAI) for Attack Detection in Wireless sensor Networks

BA, MA

State: Open

Published: 2025-02-20

The evolution of 5G and upcoming 6G networks brings ultra-low latency, massive connectivity, and higher data rates, making them essential for critical applications such as autonomous vehicles, smart cities, and industrial automation. However, the increased complexity and reliance on AI-driven network management have also introduced new cybersecurity risks, including DDoS attacks, Man-in-the-Middle (MITM) attacks, and advanced persistent threats (APTs). Traditional AI-based intrusion detection systems (IDS) are effective but often lack transparency, leading to trust and accountability issues. Explainable AI (XAI) aims to bridge this gap by making AI-based decisions interpretable, trustworthy, and auditable. This project will focus on integrating XAI into 5G/6G network security to improve attack detection and response strategies. The primary objectives of this research are:

Develop an AI-based attack detection model tailored for 5G/6G networks.
Implement Explainable AI techniques (e.g., SHAP, LIME, Grad-CAM) to make decisions interpretable.
Evaluate and compare traditional AI-based detection methods with XAI-enhanced models.
Develop a framework for real-time attack response based on XAI insights.

Some Sources to consider:

1. Ullah, Naeem, Javed Ali Khan, Ivanoe De Falco, and Giovanna Sannino. "Explainable artificial intelligence: importance, use domains, stages, output shapes, and challenges." ACM Computing Surveys 57, no. 4 (2024): 1-36.

2. Nascita, Alfredo, Giuseppe Aceto, Domenico Ciuonzo, Antonio Montieri, Valerio Persico, and Antonio Pescapé. "A Survey on Explainable Artificial Intelligence for Internet Traffic Classification and Prediction, and Intrusion Detection." IEEE Communications Surveys & Tutorials (2024).

3. Senevirathna, Thulitha, Vinh Hoa La, Samuel Marchal, Bartlomiej Siniarski, Madhusanka Liyanage, and Shen Wang. "A survey on XAI for 5G and beyond security: Technical aspects, challenges and research directions." IEEE Communications Surveys & Tutorials (2024).

4. Brik, Bouziane, Hatim Chergui, Lanfranco Zanzi, Francesco Devoti, Adlen Ksentini, Muhammad Shuaib Siddiqui, Xavier Costa-Pèrez, and Christos Verikoukis. "Explainable AI in 6G O-RAN: A Tutorial and Survey on Architecture, Use Cases, Challenges, and Future Research." IEEE Communications Surveys & Tutorials (2024).

5. Wang, Shen, M. Atif Qureshi, Luis Miralles-Pechuan, Thien Huynh-The, Thippa Reddy Gadekallu, and Madhusanka Liyanage. "Applications of explainable AI for 6G: Technical aspects, use cases, and research challenges." arXiv preprint arXiv:2112.04698 (2021).

6. Mallampati, Seshu Bhavani, and Hari Seetha. "Enhancing Intrusion Detection with Explainable AI: A Transparent Approach to Network Security." Cybernetics and Information Technologies 24, no. 1 (2024): 98-117.

7. Albashayreh, Amjad, Yahya Tashtoush, Abdallah Aldosary, Omar Darwish, and Firas Albalas. "Explainable-AI for DoS Attacks Detection in 5G Network Using Deep Learning Models." In 2024 International Conference on Intelligent Computing, Communication, Networking and Services (ICCNS), pp. 166-171. IEEE, 2024.

30% Design, 50% Implementation, 20% Documentation

ML, Python

Supervisors: Nasim Nezhadsistani

back to the main page