Deep Ensemble Learning With Pruning for DDoS Attack Detection in IoT Networks
Bibliographic record
Abstract
The upsurge of Internet of Things (IoT) devices has increased their vulnerability to Distributed Denial of Service (DDoS) attacks. DDoS attacks have evolved into complex multi-vector threats that high-volume and low-volume attack strategies, posing challenges for detection using traditional methods. These challenges highlight the importance of reliable detection and prevention measures. This paper introduces a novel Deep Ensemble learning with Pruning (DEEPShield) system, to efficiently detect both high- and low-volume DDoS attacks in resource-constrained environments. The DEEPShield system uses ensemble learning by integrating a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) network with a network traffic analysis system. This system analyzes and preprocesses network traffic while being data-agnostic, resulting in high detection accuracy. In addition, the DEEPShield system applies unit pruning to refine ensemble models, optimizing them for deployment on edge devices while maintaining a balance between accuracy and computational efficiency. To address the lack of a detailed dataset for high-and low-volume DDoS attacks, this paper also introduces a dataset named HL-IoT, which includes both attack types. Furthermore, the testbed evaluation of the DEEPShield system under various load scenarios and network traffic loads showcases its effectiveness and robustness. Compared to the state-of-the-art deep ensembles and deep learning methods across various datasets, including HL-IoT, ToN-IoT, CICIDS-17, and ISCX-12, the DEEPShield system consistently achieves an accuracy over 90% for both DDoS attack types. Furthermore, the DEEPShield system achieves this performance with reduced memory and processing requirements, underscoring its adaptability for edge computing scenarios.
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 | 0.004 |
| 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 | 0.002 |
| 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".