DeepLSTMDefense: A Recurrent Learning Framework for DDoS Detection using Network Traffic Sequences
Bibliographic record
Abstract
Distributed Denial of Service (DDoS) attacks are still making networks less available, so detection needs to be able to tell the difference between real flash-crowds and fake ones with very precise timing. This paper introduces DeepLSTMDefense, a recurrent sequence-classification pipeline. Network flows are grouped into time-ordered sequences, normalized, and windowed to keep temporal dependencies. Then, stacked Long Short-Term Memory (LSTM) layers are used to model traffic dynamics more accurately than static feature learners. We trained and tested the system using CICDDoS2019 and custom Portmap traces. Compared to classical baselines (Naïve Bayes, Support Vector Machine, Random Forest), consistent gains were made: on CICDDoS2019, the accuracy was 97.9%, the precision was 98.1%, the recall was 97.8%, and the false-alarm rate was 4.3%. This cut the overall error rate from 7.517% to 2.103% (≈72.0% relative reduction). When there was only a small amount of Portmap traffic, the error rate dropped by 39.69%, showing that it works with more than one dataset. These findings were validated by an AUC exceeding 0.98 and by confusion matrices demonstrating elevated sensitivity and specificity across various attack vectors. By framing DDoS detection as sequence classification, it became possible to establish earlier and more dependable trigger points for mitigation without compromising generalization. The stacked-LSTM design was put to use for practical, almost real-time defense.
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 | 0.001 |
| 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 | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".