Unified hybrid quantum classical neural network framework for detecting distributed denial of service and Android mobile malware attacks
Bibliographic record
Abstract
Abstract The rise of advanced networking and mobile technologies has improved flexibility in Software Defined Networking (SDN) management and mobile ecosystems but it has also introduced vulnerabilities like Distributed Denial of Service (DDoS) attacks and Android malware. In this research, we propose a Hybrid Quantum Classical Neural Network (HQCNN) framework that operates with a Dressed Quantum Circuit (DQC) to achieve efficient detection and classification of threats. The input pipeline of the HQCNN integrates Wavelet Transforms based feature pre-processing, Convolutional Neural Network based feature extraction, Linear Discriminant Analysis (LDA) for dimensionality reduction, and quantum layers for enhanced classification with less computational complexity. Experiments were conducted on the SDN DDoS Attack Dataset and the CCCS-CIC-AndMal2020 Static Dataset. Two different model variants were devised for binary and multiclass classification problems addressing various cybersecurity issues. The binary HQCNN model for SDN-based DDoS detection was implemented on AWS Braket’s real Quantum Processing Unit (QPU), achieving 99.86% accuracy, 99.85% precision, 100% recall, and a 99.88% F1-score, thereby outperforming the classical Convolutional Neural Network (CNN). The multiclass HQCNN, on the other hand, attains accuracy of 93.56%, 94.38%, and 95.13% on the 15-class, 14-class, and 12-class versions of CCCS-CIC-AndMal2020 Static, respectively, hence outperforms all existing methods. These results show that HQCNN is efficient, scalable, and very much applicable in cybersecurity, validating its real-world use effectiveness applicability in threat detection.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| 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".