Optimizing Feature Selection for Intrusion Detection: A Hybrid Approach Using Cuckoo Search and Particle Swarm Optimization
Bibliographic record
Abstract
Network security is crucial for preserving privacy and safeguarding private information.Recent laws relevant to current web services have increased the need for intrusion detection systems, which protect data and mitigate the impact of attacks.Effective feature selection is crucial for lowering dimensionality and enhancing detection accuracy to enhance the execution of IDS.The current study's objective is to offer a novel approach to feature selection by integrating Particle Swarm Optimization (PSO) and Cuckoo Search (CS) algorithms.This study evaluates the efficiency of various optimization strategies for feature selection in the CICIoT2023 dataset, which contains a wide variety of IoT attack scenarios, aimed at enhancing intrusion detection systems.To identify and prioritize the most significant features, the current methodology uses a hybrid feature selection framework that combines the advantages of both local search efficiencies from PSO and global search capabilities from CS.Following that, the chosen features are then fed into three classifiers: Multi-Layer Perceptron (MLP), Random Forest (RF), and AdaBoost.The experimental outcomes demonstrate that the CS-PSO hybrid model significantly improves attack detection accuracy, outperforming previously reported methods on the same dataset.This research contributes to advancing network security in IoT environments by addressing the growing demand for adaptive and effective IDS solutions, instilling greater confidence in the resilience of IoT networks.
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) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 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".