Enhanced Intrusion Detection in Software-Defined Networks Through Federated Learning and Deep Learning
Bibliographic record
Abstract
Software-defined networks (SDNs), while offering a revolutionary global view of the network, remain susceptible to a variety of attacks.This vulnerability necessitates innovative solutions for preserving data privacy and enhancing network security.The work presented herein introduces an innovative network anomaly detection methodology leveraging both federated learning (FL) and deep learning (DL) techniques.In contrast to traditional collaborative learning, where potential privacy compromises arise from the distribution of local training data to a central server, the proposed methodology enables each switch in the network to collect data from its connected hosts and independently train a local Long Short-Term Memory (LSTM) model.Subsequently, each switch encrypts and forwards its model parameters to the controller.Upon receipt, the controller decrypts the parameters from each switch, computes their average, and formulates a global LSTM model.This model is disseminated to every switch in the network, enabling each host to retrain its local model according to the global parameters.This iterative process is conducted multiple times to maintain the timeliness of the information.Evaluation of the proposed methodology using the UNSW-NB15 dataset, in conjunction with NF-UQ-NIDS-v2 and CICIDS2017 datasets, demonstrated its efficacy in anomaly detection, with performance exceeding a 96.75% accuracy rate.
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 | 0.002 | 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 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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".