PyTorch-based deep learning approach for real-time network traffic analysis
Bibliographic record
Abstract
As the internet continues to expand and cyber-attacks become more complex, the area of network intrusion detection (NID) has gained considerable relevance in research. NID describes the process of monitoring and analysing network traffic to identify indicators of unauthorized access, misuse, or any other malicious activity. Various machine learning techniques can automate this process and identify anomalies in network traffic as either normal or anomaly (Bhattacharyya and Kalita, 2013). This thesis focuses on a deep learning-based network intrusion detection model trained using the PyTorch framework with the NSL-KDD dataset. The NSL-KDD dataset is widely recognized and offers a comprehensive set of features. However, given its age and its limited conformity with contemporary real-world networks, this thesis also explores alternative datasets. One significant alternative is the CIC-IDS2017 dataset from the University of New Brunswick's Canadian Institute for Cybersecurity, along with other commercial options. Moreover, the thesis compares the differences and functionality of these datasets regarding accuracy, precision, modernness and ease of use. To facilitate the comparison, the presented paper starts with an introduction and description of machine learning, PyTorch, the NSL-KDD dataset and its implementation and finishes with the description of the alternative datasets. The research significantly enhances the current body of knowledge regarding the utilization of machine learning techniques and provides advantages and disadvantages of machine learning, as well as insights into the strengths and weaknesses of the datasets. Furthermore, it provides strategies for improving their effectiveness and recommendations for future research in this specific area.
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 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".