Penetration Testing of Cyber-Physical Attacks in Smart Grids Based on Partially Observable Markov Decision Process
Bibliographic record
Abstract
The smart grid is a highly complex cyber-physical system of heterogeneous components with sensory, control, computation, and communication. Its complexity, dimensionality, uncertainty, and strong cyber-physical coupling have made it inefficient to discover critical vulnerabilities at system or infrastructure levels manually. To enhance the security of smart grids, this work explores the attackers’ perspective and proposes a deep reinforcement learning (DRL)-based penetration testing (PT) framework to identify critical vulnerabilities in smart grids efficiently. Specifically, this paper takes replay attacks as an example of PT and formulates its optimization as a Partially Observable Markov Decision Process (POMDP) for DRL agents with three actions (stop, record, and replay): a partial observation model is created to mimic a real scenario where the pen-tester can only access limited intelligence. A reward function considering the PT’s multiple goals is designed to optimize the timing and ordering of replay attacks. Knowledge of the grid is further utilized to estimate the full state of the system and transform the POMDP into a Markov Decision Process (MDP) to be solved by DRL. A software-based co-simulation platform for DRL-based PT on the smart grid (GridBattleSim) was developed to validate our proposed PT framework.
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) | 0.001 | 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 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".