Multi-Domain Deep Reinforcement Learning for Cyber-Physical Systems Security on the WDT Testbed Dataset
Bibliographic record
Abstract
Cyber-Physical Systems (CPS) are becoming increasingly vulnerable to coordinated attacks that target both the network and physical layers. Traditional intrusion detection systems typically treat these domains separately, limiting their ability to detect complex, cross-domain threats. In this paper, we investigate the feasibility of training a unified reinforcement learning agent that can simultaneously detect anomalies in both domains. Using the publicly available Water Distribution Testbed (WDT) dataset, we evaluate and compare the performance of three Deep Reinforcement Learning (DRL) algo-rithms-Asynchronous Advantage Actor-Critic (A3C), Dueling Deep Q-Network (Dueling DQN), and Proximal Policy Optimization (PPO). Our experiments demonstrate that Dueling DQN consistently achieves the highest reward and fastest convergence in both single-domain settings. We then develop a domainaware dual-branch Dueling DQN agent, which achieves a rolling reward of 161.99 on the unified dataset-surpassing the physicalonly model and approaching the network-only baseline. These results suggest that a shared DRL policy can generalize across domains while reducing deployment complexity in CPS security applications.
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".