A Novel CNN Model with Dimensionality Reduction for WSN Intrusion Detection
Bibliographic record
Abstract
Wireless sensor networks (WSNs) play a critical role in cyber-physical systems, enabling communication between autonomous sensors. When integrated with the Internet of Things (IoT), WSNs unfortunately become vulnerable to various attacks, such as blackhole, grayhole, flooding, and scheduling, thereby posing significant security threats. Existing methods for intrusion detection in WSNs often suffer from low detection rates, significant computational overhead, and false alarms, primarily due to resource constraints and data correlations. This study introduces IDS-CNN, a novel intrusion detection method leveraging Convolutional Neural Networks (CNNs). The proposed IDS-CNN model, designed to optimize efficiency and reduce processing time, comprises nine convolutional neural network layers and six Max-Pooling1D layers. To alleviate computational demands, dimensionality reduction techniques, specifically Principal Component Analysis and Singular Value Decomposition, are applied to raw traffic data. The IDS-CNN model is then employed to classify and categorize network threats. Experimental evaluations suggest that the IDS-CNN approach yields a high accuracy rate of 99% compared to existing methods, based on tests performed on two datasets, WSN-DS and UNSW-NB15. Notably, with the UNSW-NB15 dataset, accuracy rates were further improved to 99.99% and 100%. By leveraging deep learning techniques to enhance intrusion detection in WSNs, this study presents a significant contribution to the field. The IDS-CNN model advances our understanding of WSN security by exceeding the accuracy rates of prior models. As it addresses the limitations of existing methods, the implications of this research are substantial, offering a more reliable and efficient solution for WSN intrusion detection. The findings underscore the potential of IDS-CNN in safeguarding WSNs and IoT systems from sophisticated and evolving cyber threats.
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 | 0.001 | 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) | 0.002 | 0.001 |
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".