Slice-Specific Machine Learning Models for Intrusion Detection in 5G Telecommunication Networks
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The security challenges introduced by 5G network slicing demand tailored intrusion detection systems (IDS). Traditional intrusion detection systems (IDS) and intrusion detection and prevention systems (IDPS) frameworks, built for static network configurations, are inadequate for the dynamic and heterogeneous nature of 5G networks. To address this gap, this study develops and evaluates slice-specific machine learning models to enhance intrusion detection across different 5G slices, namely: enhanced Mobile Broadband (eMBB), massive Machine-Type Communication (mMTC), and Ultra-Reliable Low-Latency Communication (URLLC). Random Forest, Support Vector Machine (SVM), and Long Short-Term Memory (LSTM) models were applied to publicly available datasets representing each slice. These models are assessed based on their accuracy, precision, recall, F1-score, area under the receiver operating characteristic curve (AUC-ROC), confusion matrix and execution time. The results reveal that the LSTM model achieved the highest accuracy and AUC-ROC scores for the eMBB and mMTC slices, making it suitable for applications where detection accuracy is critical despite higher computational demands. In contrast, Random Forest demonstrated superior computational efficiency, making it the most preferred model for latency-sensitive URLLC slice, where real-time detection is essential. While the SVM model performed well in terms of accuracy, its high computational cost renders it less practical for real-time applications, particularly in URLLC environments. This research provides insights for enhancing 5G network security through the deployment of slice-specific machine learning models, thereby addressing the critical need for adaptable and efficient IDS frameworks.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it