CBFF-LSTM: a deep learning framework for early-stage DOS attack detection in IOT-enabled WSN through correlated behavioural feature fusion
Bibliographic record
Abstract
Denial-of-Service (DoS) attacks pose significant threats to Internet of Things-enabled Wireless Sensor Networks (IoT-WSN) due to device vulnerabilities and resource constraints, leading to network disruptions and service degradation. Existing approaches primarily focus on post-attack detection and classification. This paper proposes a novel deep learning framework called Correlated Behavioural Feature Fusion with Long Short-Term Memory (CBFF-LSTM) for proactive early-stage DoS attack detection with minimal computational overhead in IoT-WSN environments. The CBFF-LSTM framework introduces three key innovations (1) a progressive four-stage detection mechanism enabling early attack identification, (2) a novel Correlated Behavioral Feature (CBF) extraction methodology that simultaneously analyzes spatial–temporal dependencies at both node and network levels, and (3) an adaptive Feature Fusion Vector (FFV) generator optimized for resource-constrained IoT devices. Experimental validation was conducted using NS-3 simulator, incorporating diverse attack scenarios. A performance with 98.4% detection accuracy under controlled simulation (realistic expectation: 94–96%), 1.4% false positive rate (expected real-world: 2–4%), and early detection (2.3 s average) was achieved. The framework achieves linear scalability O(n) with inference times of 1.8 ms per sample and resource efficiency below 6% CPU usage, making it suitable for resource-constrained IoT environments while providing predictive capabilities not achieved by existing LSTM and feature fusion combinations.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 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".