A Stable Generative Adversarial Network Architecture for Network Intrusion Detection
Bibliographic record
Abstract
Many approaches have been proposed for detecting and categorizing malicious activities over the years. The adversarial training process has recently been applied to solve this task, yielding remarkable results. Generative Adversarial Networks (GANs) can model complex distributions of high-dimensional data, which is useful for anomaly detection. Few studies have examined the use of GANs to detect network intrusions. This paper aimed to develop a new architecture for generative and discriminative training to improve the detection of multi-attack types with a stable training process using ensemble convolutional neural networks (CNNs). By applying the stacking ensemble learning method to the public datasets, NSL-KDD and UNSW-NB15, efficient intrusion detection is achieved compared to the state-of-the-art performance. Additionally, the training process is more stable with this novel architecture, and the model converges faster. The proposed method's accuracy, precision, sensitivity, and F1 score are obtained at 86.36%, 86.29%, 86.36%, and 85.81% for the NSL_KDD dataset, respectively. For the UNSW-NB15 dataset, the accuracy, precision, sensitivity and F1 score are 89.43%, 91.51%, 89.44%, and 89.72%, respectively.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 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".