Balancing QoS and Security in the Edge: Existing Practices, Challenges, and 6G Opportunities With Machine Learning
Bibliographic record
Abstract
While the emerging 6G networks are anticipated to meet the high-end service quality demands of the mobile edge users in terms of data rate and delay satisfaction, new attack surfaces and zero-day attacks continue to pose significant threats to their successful realization and rollouts. Traditionally, most service provisioning techniques considered security metrics separately from the Quality of Service (QoS) and Quality of Expectation (QoE) parameters. The QoS/QoE parameters include data throughput, experienced delay, tolerable latency, jitter, resource utilization rate, spectral efficiency, energy efficiency, fairness, and other emerging key performance indicators (KPIs). Also, there are various security attributes, such as encryption key strength, authentication strength, network anomaly score, privacy metric, and so on. Typically the resource allocation optimization techniques to maximize the security aspects to protect the communication of mobile users or user equipment (UEs) have an adverse effect on the service quality. Therefore, a key research gap exists in balancing service quality and security levels in communication networks that has been either overlooked or identified in a rather scattered manner by researchers in the recent decade. Thus, a comprehensive survey of the state-of-the-art to clearly address this research gap and outline the possible solutions is yet to appear in the existing literature. In this paper, we address this by surveying the existing practices, challenges, and opportunities in the emerging 6G (i.e., beyond 5G) networks, where various AI (Artificial Intelligence)-based techniques such as deep learning meet the classical optimization techniques, to balance the service performance and security levels. Several networking topologies with relevant use-cases are included in the survey to discuss the existing and emerging trends of isolated as well as joint treatment of service and security levels. Lessons learned from each use-case are provided to demonstrate a clear road map for the interested readers and researchers in emerging networks to construct a natively combined service and security ecosystem, specifically in the network edge.
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 | 0.003 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.007 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".