Anomaly Detection in Air-Gapped Industrial Control Systems of Nuclear Power Plants
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This paper proposes to combine two neural network models to detect anomalous behaviors resulting from cyber-threats in air-gapped industrial control systems (ICS) specific to nuclear power plant’s (NPP) safety shutdown systems. Initially, an ICS testbed that replicates essential components of NPP safety protocols is developed, providing a realistic environment for model validation. The proposed model uses the strengths of a native transformer and Long Short-Term Memory (LSTM) networks. This combination not only detects denial of service (DoS) attacks but sophisticated threats like man-in-the-middle (MITM) attacks. Experimental results show that the combined model has a detection accuracy of 99.8% using a dataset characterized by balanced classes across MITM and DoS scenarios. The model is presented as a white-box solution, facilitating straightforward implementation and adoption by NPP system owners who seek transparency and control over their security measures.
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.
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 it