Secure SDN-IOT Framework with Adaptive Gbell PRF-MAC and Convolutional GRU for IDS
Bibliographic record
Abstract
The increasing integration of IoT devices into modern infrastructures necessitates robust frameworks to secure data transmission and enhance network performance. This paper presents a secure Software-Defined Networking (SDN)-IoT framework that combines adaptive Gbell Probability-Based Fuzzy Rule Matching (Gbell PRF-MAC) and Convolutional GRU (CGRU) for Intrusion Detection Systems (IDS). The proposed framework demonstrated exceptional performance in addressing key challenges of data security and SDN layer efficiency. It employed Gbell PRF-MAC to create and validate adaptive Message Authentication Codes (MACs) with optimal timings of 1789ms for generation and 2234 ms for verification, ensuring robust validation while expediting user identification for secure SDN access. Simultaneously, IoT data transmission was safeguarded using adaptive encryption, achieving an impressive security level (SL) of 99.12%. For intrusion detection, the CGRU model achieved a remarkable accuracy of 99.86%, effectively distinguishing between attack and non-attack scenarios through optimized feature selection, which also minimized computational overhead. Additionally, the integration of SDN intelligence and IoT adaptability enabled dynamic Service Level Agreement (SLA) management, achieving a response time of 1449 ms and ensuring smooth and efficient service delivery. This synergy between advanced security mechanisms and SDN-IoT flexibility provides a robust, scalable, and adaptive solution for modern infrastructures. The proposed framework not only mitigates evolving cyber threats but also enhances data security and network efficiency, establishing a comprehensive approach to secure IoT-based ecosystems. This study demonstrates its potential to be a cornerstone for secure and efficient next-generation IoT implementations.
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 | 0.001 |
| 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 | 0.001 | 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".