fDoS: Explainable AI-Based Federated Learning for DDoS Detection in IoT Networks
Bibliographic record
Abstract
The growing number of Internet of Things (IoT) devices and embedded technology has created them popular targets for intrusions such as DDoS and malware, creating serious security problems. These attacks diminish network performance and pose privacy and data integrity issues in IoT environments. Existing centralized detection mechanisms struggle with scalability and data privacy concerns, highlighting the need for a distributed yet efficient solution. This study proposes a Federated Learning (FL)-based framework to detect DDoS attacks by incorporating a dual-stage feature mining approach using Recursive Feature Elimination (RFE) and correlation-based filtering to identify the most relevant and non-redundant features. Additionally, Explainable AI (XAI) techniques are integrated to enhance model transparency, allowing for better interpretability of feature contributions. Gradient boosting is the classification model used to achieve high accuracy while adapting to dynamic attack patterns. FL’s distributed design guarantees that the system is suitable for real-time deployment in IoT networks, since it processes data locally at edge devices without transferring critical information. The developed fDoS gives an accuracy of 99.73%, outperforming traditional centralized and distributed approaches in detection accuracy and computational efficiency. This solution enhances IoT network security by providing a scalable, privacy-preserving, and computationally efficient framework for detecting and mitigating DDoS attacks in real-time.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| 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".