Optimizing DDoS Detection with Time Series Transformers
Bibliographic record
Abstract
Distributed Denial of Service (DDoS) attacks pose severe risks to large networks by disrupting services. Effective detection and response are crucial. Despite progress, current DDoS detection methods need improvement in adaptability and scalability to manage growing network traffic complexity. Existing models often fail to generalize across various network environments, protocols or attack types. This research introduces a hybrid model combining a Time Series Transformer (TST) with feature engineering to enhance DDoS detection and classification. Based on an experimental evaluation using the CICDDoS2019 and CICIoT2023 datasets, which encompass diverse DDoS attack types and network environments, the proposed model outperforms RNN, BiLSTM, and TransformerRNN models. The TST approach achieved an accuracy of 0.971 and an F-beta score of 0.701 on the CICDDoS2019 dataset, and an accuracy of 0.981 and an F-beta score of 0.952 on the CICIoT2023 dataset. We also compare the TST approach's performance across different network protocols for DDoS classification, analyzing the model's ability to detect attacks within various protocols, such as TCP, UDP, and ICMP.
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 | 0.003 |
| 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 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".