Multimodal Game-Theoretic Cyber-Attack Projection in Industrial Control Systems
Bibliographic record
Abstract
Securing Industrial Control Systems (ICS) can be challenging, as solutions developed for general Information Technology (IT) systems may be less effective in an ICS setting. Moreover, most available cybersecurity solutions in ICS are only focused on the classic problem of detecting cyber-attacks and anomalies. However, these solutions cannot provide extended information to security experts to stop the attack or the source of the abnormality. Thus, this paper propose a cutting-edge multimodal data-driven strategy by integrating Deep Reinforcement Learning (DRL) and Deep Neural Networks (DNNs). In contrast to conventional cybersecurity approaches primarily centered on detecting cyber-attacks and anomalies, the proposed method delves into analyzing the behavioral patterns of attackers within an ICS environment. Leveraging reinforcement learning, the approach anticipates the subsequent actions of potential threats. This wealth of additional information empowers security experts to proactively stay ahead of evolving risks, facilitating preemptive measures to thwart impending attacks. The effectiveness and scalability of this multimodal data-driven approach are demonstrated through evaluation on water treatment systems, showcasing its ability to accurately predict and prevent cyber-attacks within the ICS environment.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".