Dynamic Real Time Framework for Abnormal Detection of IMS Core in Kubernetes Cloud
Bibliographic record
Abstract
In the ever-evolving telecommunications sector, advancing from 5G towards 6G, maintaining the security of core infrastructures has become supreme. This study addresses the critical need for proactive and real-time anomaly detection within cloud-native environments. Leveraging cloud-native implementations within Kubernetes clusters, our framework utilizes advanced machine learning techniques to analyze data from applications and clusters. Specifically, this paper introduces a novel integration of k-means clustering and Long Short-Term Memory (LSTM) models for real-time anomaly detection in Kubernetes-based cloud-native environments, offering a unified framework capable of addressing both global and local anomalies across multiple layers of the IP Multimedia Subsystem (IMS) core. Existing research on anomaly detection in Kubernetes environments often focuses on specific application layers or isolated metrics, lacking a comprehensive solution that addresses the multidimensional and dynamic nature of IMS core anomalies across application, pod, and node levels in real-time. By employing k-means clustering and LSTM models, our approach achieves approximately 90% accuracy in anomaly detection. Extensive experiments with various model versions demonstrate the effectiveness of the framework, ensuring robust security and reliability for next-generation telecom networks.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".