A Resilient Machine Learning-Driven Multi-Layered Security Model for Modern Cyberspace
Bibliographic record
Abstract
The increasing heterogeneity of cyber threats emphasizes the inadequacy of traditional, single technique security models. Existing models often emphasize perimeter defence, anomaly detection, or access control in isolation, leaving systems vulnerable to advanced consistent threats, attacks from insiders, and data integrity compromise. This escalating advancement of cyber threats, therefore, demands resilient, adaptive, and auditable cybersecurity models that is beyond traditional single-layered defences. This study presents the Multi-Layered Cybersecurity Model (MLCM), which is a hybrid model architecture that integrates three complementary principles: artificial intelligence (AI)-driven intrusion detection systems (IDS), blockchain-based integrity management, and zero-trust access control. Using the Canadian Institute for Cybersecurity Intrusion Detection System 2017 (CICIDS2017) benchmark dataset, a hybrid CNN–BiLSTM intrusion detection model was trained and validated, achieving 98.6% detection accuracy, 98.3% F1-score, Receiver Operation Curve – Area Under the Curve (ROC-AUC) macro of 99.1% and a false positive rate of 1.75%, outperforming standalone CNN (94.8%) and LSTM (95.6%) baselines. The incorporation of blockchain into the model ensured impervious logging with average transaction latency of 0.45 seconds, while Zero-Trust Access policies reduced unauthorized edgewise movements by 84.5% during simulation. The multi-layer feedback loop demonstrated strong flexibility under malicious and incomplete data conditions, maintaining over 96% accuracy despite 9% feature loss. These results support the model’s robustness, scalability, and applicability to national cybersecurity strategies, particularly in resource-constrained environments like Nigeria. The MLCM therefore offers a pathway toward strong, flexible, AI-enhanced, and policy-based digital defence in the modern threat landscape as well as advancing resilient digital infrastructures in the era of increasing connectivity. Keywords: Multi-layered security, Resilience, Blockchain, Zero-trust access, artificial intelligence Article Citation Format Afolorunso, A.A., Adeniyi, A.E., Abiodun, A.O., Oyewande, O.V. & Garki, F.S. (2025): A Resilient Machine Learning-Driven Multi-Layered Security Model for Modern Cyberspace. Journal of Digital Innovations & Contemporary Research in Science, Engineering & Technology. Vol. 13, No. 3. Pp 27-42 www.isteams.net/digitaljournal dx.doi.org/10.22624/AIMS/DIGITAL/V13N3P3
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 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 | 0.021 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.004 | 0.009 |
| Science and technology studies | 0.008 | 0.002 |
| Scholarly communication | 0.005 | 0.009 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.000 | 0.004 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".