A Machine Learning and Heuristic Hybrid Approach for Detecting LDoS Attacks Using Hyperparameter Optimization
Bibliographic record
Abstract
In today’s digitized world, people rely heavily on numerous smart machines to perform everyday tasks. The number of smart devices has surged recently, leading to an increase in security vulnerabilities. Among these, the “Low-rate denial of service (LDoS)” attack stands out as particularly dangerous due to its stealthy and varied nature, posing significant challenges for current intrusion detection systems. This research introduces a hybrid approach to investigate LDoS attack features, combining hyperparameter optimization (HPO) with principal component analysis (PCA). To address dataset imbalance, the SMOTE technique is applied. PCA is used for dimensionality reduction, with the key hyperparameter ’n_components’ optimized through HPO. The study utilizes the ‘CICIDS2017’ and ‘CSECISDOS2018’ datasets, highlighting the importance of dimension reduction for improved performance. The hybrid method, termed HPO-S-PCA, is employed to analyze LDoS traffic features and extract relevant features. The research observed a trade-off between True Positive Rate (TPR) and accuracy in existing studies and focused on enhancing both performance metrics through the novel hybrid approach. Machine learning classifiers such as ‘Logistic Regression (LR)’, ‘Support Vector Machine (SVM)’, ‘Decision Tree (DT)’, ‘Random Forest (RF)’, ‘K-Nearest Neighbors (KNN)’, ‘Kernel SVM’, and ‘Naive Bayes (NB)’ were trained to detect LDoS attacks using the extracted features. Among these, RF and KNN classifiers achieved 99.9% detection rate for positive anomalies. PCA with best n_components perform well and provide expected results for MRE and EVR. K-Nearest Neighbors outperforms all based on accuracy, TPR, MRE and EVR.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".