ME-IDS: An Ensemble Transfer Learning Framework Based on Misclassified Samples for Intrusion Detection Systems
Bibliographic record
Abstract
In our digitally interconnected world, the demand for robust security measures has become increasingly apparent, given the escalating threat of cyberattacks on the Internet. Intrusion Detection Systems (IDS) have emerged as vital safeguards for Internet network infrastructure. Despite the significant advancements in IDS over the past decades, there remains much room for improvement, especially with recent advances in machine learning and deep learning. In this paper, we propose a Misclassified sample based Ensemble transfer learning framework for IDS (ME-IDS) in order to effectively detect malicious intrusions. Technically, ME-IDS employs frequency encoding to handle categorical features and utilizes a feature selection method to mitigate the curse of dimensionality. In addition, it leverages three hyper-parameter-tuned variants of a transfer learning model in its ensemble learning stage, ultimately resulting in high detection accuracy. Our experimental results based on a publicly available IDS dataset, UNSW-NB15, indicate that ME-IDS leads to an impressive accuracy of 99.72%, significantly outperforming the state-of-the-art detection systems.
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 | 0.004 | 0.009 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| 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".