Detection of DDoS Attack Using Machine Learning Models
Bibliographic record
Abstract
Distributed Denial of Service (DDoS) attacks remain one of the fastest-moving threats in cybersecurity, attacking important network infrastructure through flooding systems with malicious traffic and thereby degrading legitimate services. This paper envisions an end-to-end framework using machine learning (ML) for enabling precise and effective DDoS attack detection, using the CICIDS2017 benchmark dataset provided by the Canadian Institute for Cybersecurity. We conduct a systematic comparison of six supervised learning algorithms-K Nearest Neighbor (KNN), Support Vector Machine (SVM), Neural Net- works (NN), Random Forest, CatBoost, and XG Boost-with the aim of determining the topperforming model to discriminate between benign and malicious traffic patterns. Our approach is centered around rigorous data preprocessing, feature engineering, and hyperparameter tuning for ensuring generalizability and bypassing the challenge of overfitting. Experimental results indicate that ensemble-based approaches, i.e., Random Forest, CatBoost, and XGBoost, achieve near perfect classification accuracy (99.9%) with enhanced precision, recall, and F1-scores relative to conventional models like KNN and SVM. In addition, we assess computational efficiency and interpretability of the models to support practical deployment within real-world network environments. This paper not only confirms the potency of advanced ensemble methodologies in the detection of DDoS attacks but also presents a scalable, data-driven framework that can be modified to new emerging attack vectors. Future extensions include improvements in real time detection performance and adversarial robustness testing to combat zeroday attacks.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| 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".