Hybrid BiLSTM-SVM Intrusion Detection with Decision-Based Flow Ranking
Bibliographic record
Abstract
Intrusion Detection Systems (IDS) are important in facing the development of cyber threats such as Distributed Denial of Service (DDoS), phishing, and malware attacks, so, their promulgating is important.Bidirectional Long Short-Term Memory (BiLSTM) with Support Vector Machines (SVM) has been integrated and proposed as a hybrid model in this paper to improve detection accuracy and threat response.The proposed system steps include comprehensive data preprocessing, feature extraction using BiLSTM, and classification with SVM, and all these using and leveraging the UNSWNB15 dataset.Deep learning takes advantage of BiLSTM's ability and traditional machine learning leverage from SVM's efficiency so this integration captures temporal patterns through BiLSTM and manages high-dimensional data through SVM.Experimental findings showed that the proposed system is accurately proficient in distinguishing between normal and attack traffic, achieving high levels of accuracy values, such as precision 95%, recall 94%, and F1-scores 95%, where the accuracy value reaches 99%.Besides, to improve the efficiency of threat management, SVM's decision function scores have been used to employ a ranking technique by the proposed system.Therefore, this research highlights the hybrid model value in enhancing IDS performance.
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 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| 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".