Interactive and Explainable Optimized Learning for DDoS Detection in Consumer IoT Networks
Bibliographic record
Abstract
The integration of Internet of Things (IoT) in consumer environments enhances convenience and security while increasing Human-Computer Interaction (HCI). However, this increased interactivity has also increased the vulnerability of Consumer IoT (CIoT) networks to cyber threats, mainly Distributed Denial of Service (DDoS) attacks. The DDoS attacks, which vary in volume, present substantial challenges to these networks’ operational integrity and customer trust. This paper introduces the Artificial Intelligence (AI)-driven (ADEPT) system that utilizes explainable and optimized deep-ensemble learning with pruning for DDoS detection. The system uses attention-based ensemble DL for DDoS detection, combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks. To address the resource constraints of edge devices in CIoT networks, the system uses Differential Evolution (DE)-based pruning and quantization techniques, optimizing the model for efficient deployment on edge nodes while preserving high performance. An HCI interface is designed to allow network administrators and researchers to engage with the system through dynamic visualizations, facilitating complex data interpretation and empowering administrators to refine detection strategies. The interface, integrating SHapley Additive exPlanations (SHAP) and risk assessment, enhances model transparency and interpretability, highlighting the synergy of HCI and AI. The ADEPT system is evaluated using an experimental testbed and CIoT datasets and has demonstrated over 90% accuracy in detecting high- and low-volume DDoS 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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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".