Multiclass Feature Selection Model for Adversarial Attacks in IoT Environment
Bibliographic record
Abstract
Malware attacks have become prevalent in the uti-lization of Internet of Things (IoT) networks. The security and re-liability of IoT networks and information systems are significantly threatened by this. Machine learning-based Intrusion Detection Systems (IDS) are ineffective in countering these cyber threats due to the widespread distribution of malware. This research presents a method for choosing features that utilize Generative Adversarial Networks (GAN) to enhance the effectiveness of Intrusion Detection Systems (IDS) by reliably and promptly identifying both new and previously known threats in real-time in the IoT environment. Our feature selection method consists of two parts. First, we employed the Mutual Information (MI) technique to reduce the required features. Second, we employed exclusion and inclusion feature selection techniques which rely on discriminator accuracy to detect adversarial attacks. We performed an experiment using the proposed method on the CICIOT 2023 dataset, which includes a diverse range of IoT attack incidents. To the best of our knowledge, our proposed effort is the initial endeavor to utilize a feature selection method on this recently introduced dataset. The selection of 20 features for generating new data with optimal evaluation accuracy was accomplished using a Convolutional Neural Network (CNN) and a Mutual Information Classifier, incorporating exclusion and inclusion techniques. Ultimately, we utilized a Recurrent Neural Network (RNN) with a limited set of features to classify malware attacks. Subsequently, we evaluated the correctness of the classification by considering prominent features, resulting in a commendable accuracy rate of 93%.
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 | 0.002 | 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) | 0.001 | 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".