A Collaborative DNN-Based Low-Latency IDPS for Mission-Critical Smart Factory Networks
Bibliographic record
Abstract
Industrial Control Systems (ICSs) have entered an era of modernization enabled by the recent progress in Information Technologies (IT), particularly the Industrial Internet of Things (IIoT). This enables better automation of industrial processes but now exposes the ICSs to cyber-attacks that exploit the IIoT vulnerabilities. Thus, to ensure ICSs security, numerous research works have focused on designing Intrusion Detection and Prevention Systems (IDPSs), and deep learning has recently received considerable attention, as it has the potential to improve detection accuracy. However, most of the proposed deep learning solutions focus only on the model’s accuracy without considering latency, which is an essential requirement in many ICSs. The novelty of this paper is the time complexity analysis of Deep Neural Networks (DNNs) and the design of a low latency and robust deep learning-based collaborative IDPS. The proposed architecture employs two classification models. In the first model, a lightweight DNN is used to perform a binary classification, i.e., normal or attack, which ensures rapid intrusion detection. A second model ensures the identification of the type of attacks by performing a multi-class classification of the detected anomaly, which is handled by a robust and complex DNN in order to achieve higher accuracy. This research also proposes intrusion response measures to deal with detected attacks, first after the anomaly detection, and then after the identification of the attack type. An experimental evaluation has been provided using various detection features, datasets, DNN algorithms, and the results demonstrate the effectiveness of the proposed solution.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 teacher head, 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".