Integration of metaheuristic based feature selection with ensemble representation learning models for privacy aware cyberattack detection in IoT environments
Bibliographic record
Abstract
The Internet of Things (IoT) connects virtual and physical objects inserted with software, devices, and other technology that interchange data utilizing the Internet. It enables diverse devices and individuals to exchange data, interconnect, and personalize services to ease usage. Despite IoT's merits, rising cyberthreats and the rapid growth of smart devices increase the risk of data breaches and security attacks. The increasing complexity of cyberattacks demands advanced intrusion detection systems (IDS) to defend crucial assets and data. AI techniques such as machine learning (ML) and deep learning (DL) have shown robust potential in improving IDS performance by accurately detecting and classifying malicious network behavior in IoT environments. This manuscript proposes an Adaptive Metaheuristic-Based Feature Selection with Ensemble Learning Model for Privacy-Preserving Cyberattack Detection (AMFS-ELPPCD) technique. The data normalization stage initially applies Z-score normalization to convert input data into a beneficial format. The AMFS-ELPPCD model utilizes the adaptive Harris hawk optimization (AHHO) model for the feature process selection of the subset. Furthermore, ensemble models such as bidirectional gated recurrent unit (BiGRU), Wasserstein autoencoder (WAE), and deep belief network (DBN) are used for the classification process. Finally, social group optimization (SGO) optimally adjusts the ensemble classifiers' hyperparameter values, resulting in better classification performance. A set of simulations is performed to exhibit the promising results of the AMFS-ELPPCD under dual datasets. The experimental validation of the AMFS-ELPPCD technique portrayed a superior accuracy value of 99.44% and 98.85% under the CICIDS-2017 and NSLKDD datasets over existing models.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| 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) | 0.000 | 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 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".