A digital twin and deep-learning ensemble for cyber attack detection in industrial control systems at the IoT edge
Ali Sayghe, Mohammad D Alahmadi, Abdulrahman A Gharawi · 2026
Read A digital twin and deep-learning ensemble for cyber attack detection in industrial control systems at the IoT edge by Ali Sayghe, Mohammad D Alahmadi, Abdulrahman A Gharawi (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13402577.txt.
Description
Ali Sayghe and colleagues built a cyber-defense system that pairs a digital twin with deep learning to catch attacks on industrial control systems. Their 2026 paper addresses water treatment, distribution, and chemical plants, where attackers now use artificial intelligence to evade standard defenses. A physics-consistent virtual replica can check whether sensor data obey plant physics.
The twin, a state-space model with a Kalman filter, predicts each sensor reading and flags deviations, gating scores from a memory network, a transformer, and an isolation forest. Across 56 attack scenarios in three benchmark datasets, the system reached 97.6 percent precision, 96.2 percent recall, and sub-50-millisecond latency, beating the best single baseline by 3.2 F1 points. The paper offers a fast, interpretable defense, pending tests on live plants.
Catalog record
| CREATOR | Ali Sayghe, Mohammad D Alahmadi, Abdulrahman A Gharawi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |