On cyber security evaluations in smart grid using machine learning
Bibliographic record
Abstract
The smart grid aims to enhance the electric grid’s dependability, security, and effciency by deploying digital information and control technology. However, the increasing reliance on communication technology exposes these systems to cyberattacks, posing signifcant cyber threats to the availability and functionality of the smart grid. To mitigate such threats, effective intrusion detection algorithms are crucial. In this context, we propose a hybrid deep learning algorithm that focuses on distributed denial of service (DDoS) attacks on the communication infrastructure of the smart grid. The proposed algorithm combines convolutional neural network (CNN) and gated recurrent unit (GRU) algorithms to provide real-time analysis and state estimation-based techniques for effcient control implementation. We conduct simulations using a benchmark cyber-security dataset from the Canadian institute of cybersecurity intrusion detection system. The results demonstrate that our hybrid deep learning algorithm outperforms existing intrusion detection algorithms, achieving an impressive overall accuracy rate of 99.7 %. In the context of supervisory control and data acquisition (SCADA) systems, which monitor and control industrial machinery, communication network vulnerabilities can lead to cyber-attacks introducing false data into the operational network. We propose a restricted Boltzmann machine-based nature-inspired artifcial root foraging optimization algorithm for identifying and classifying cyber-attacks to address this issue. We optimize data features using this algorithm and evaluate its performance against traditional supervised machine learning algorithms such as artifcial neural networks, convolutional neural networks, and support vector machines. The proposed algorithm outperforms its counterparts in accuracy, precision, recall, and f1 score. Furthermore, we address the security vulnerabilities in SCADA systems by introducing the genetically seeded fora transformer neural network (GSFTNN) intrusion detection algorithm. Unlike signature-based methods, GSFTNN detects changes in operational patterns indicative of intruder involvement. We evaluate the proposed algorithm using the WUSTL IIOT 2018 ICS SCADA cyber security dataset and demonstrate its superiority over traditional algorithms like residual neural networks, recurrent neural networks, and long short-term memory (LSTM) in terms of accuracy and effciency.
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 | 0.004 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 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) | 0.001 | 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".