An empirical assessment of ML models for 5G network intrusion detection: A data leakage-free approach

Data leakage during machine learning (ML) preprocessing is a critical issue where unintended external information skews the training process, resulting in artificially high-performance metrics and undermining model reliability. This study addresses the insufficient exploration of data leakage across diverse ML domains, highlighting the necessity of comprehensive investigations to ensure robust and dependable ML models in real-world applications. Significant discrepancies in model performance due to data leakage were observed, with notable variations in F1 scores and ROC AUC values for the Breast Cancer dataset. The Tic-Tac-Toe Endgame dataset analysis revealed the varying impact on models like Ridge, SGD, GaussianNB, and MLP, underscoring the profound effect of data leakage. The German Credit Scoring dataset showed slight enhancements in recall and F1 scores for models like DT and GB without data leakage, indicating reduced overfitting. Additionally, models such as PassiveAggressive, Ridge, SGD, GaussianNB, and Nearest Centroid exhibited shifts in performance metrics, highlighting the intricate response to data leakage. The study also revealed raw data leakage rates, such as 6.79% for Spambase and 1.99% for Breast Cancer. These findings emphasize meticulous data management and validation to mitigate leakage effects, which is crucial for developing reliable ML models.

show abstract

Survey on 5G Physical Layer Security Threats and Countermeasures

Harvanek,

Bolcek,

Kufa

et al. 2024

Sensors

View full text Add to dashboard Cite

With the expansion of wireless mobile networks into both the daily lives of individuals as well as into the widely developing market of connected devices, communication is an increasingly attractive target for attackers. As the complexity of mobile cellular systems grows and the respective countermeasures are implemented to secure data transmissions, the attacks have become increasingly sophisticated on the one hand, but at the same time the system complexity can open up expanded opportunities for security and privacy breaches. After an in-depth summary of possible entry points to attacks to mobile networks, this paper first briefly reviews the basic principles of the physical layer implementation of 4G/5G systems, then gives an overview of possible attacks from a physical layer perspective. It also provides an overview of the software frameworks and hardware tool-software defined radios currently in use for experimenting with 4G/5G mobile networks, and it discusses their basic capabilities. In the final part, the paper summarizes the currently most promising families of techniques to detect illegitimate base stations—the machine-learning-based, localization-based, and behavior-based methods.

show abstract

An empirical assessment of ML models for 5G network intrusion detection: A data leakage-free approach

Cited by 3 publications

References 38 publications

Towards robust and efficient intrusion detection in IoMT: a deep learning approach addressing data leakage and enhancing model generalizability

Towards robust and efficient intrusion detection in IoMT: a deep learning approach addressing data leakage and enhancing model generalizability

Implications of Data Leakage in Machine Learning Preprocessing: A Multi-Domain Investigation

Survey on 5G Physical Layer Security Threats and Countermeasures

Contact Info

Product

Resources

About