A deep learning framework for cyberattack detection and classification in Industrial Control Systems
Bibliographic record
Abstract
The rapid integration of network-based control systems vulnerabilities within Industrial Control Systems (ICS) has increased exposure to sophisticated cyberattacks, especially in the chemical process industry. Adversaries exploit these systems by manipulating sensor data, disrupting operations, and compromising safety while remaining undetected by conventional fault detection mechanisms. Cyberattacks on critical infrastructure have become the new normal, with the World Economic Forum (WEF) ranking cyber threats as the seventh highest global risk in terms of likelihood over the next decade. Additionally, cybercrime has surged by 600% since COVID-19, highlighting the urgency of robust cybersecurity frameworks. This research introduces a hybrid cybersecurity framework combining an enhanced Typicality and Eccentricity Data Analytics (TEDA) algorithm with a Convolutional Neural Network (CNN) for real-time cyberattack detection and classification in ICS. The enhanced TEDA algorithm leverages a sliding window mechanism for adaptive statistical analysis and employs a characteristic model for detecting sophisticated cyber threats, enabling rapid anomaly identification and mitigation without requiring extensive historical data. Simultaneously, the CNN classifier accurately identifies attack types, facilitating timely mitigation strategies. Experimental validation on a laboratory-scale ICS demonstrates the framework’s effectiveness against various cyberattacks, including Min-Max, Surge, Ramp, and Replay attacks. Results highlight its adaptability, lightweight design, and real-time performance, making the proposed framework a scalable and deployable solution for enhancing ICS cybersecurity and operational resilience.
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 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 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".