A Resilient Control Strategy for Train-to-Train Communications under Jamming Attacks
Bibliographic record
Abstract
Communication-Based Train Control (CBTC) systems rely on wireless communications to enhance the efficiency of railway operations. Classical CBTC systems incorporate bidirectional train-to-wayside (T2W) communications through which trains send their status information to wayside units. T2T-CBTC systems represent a burgeoning direction in the future of CBTC. They adopt train-to-train (T2T) communications for adjacent trains to share status information. T2T communications simplify the architecture of traditional CBTC networks and reduce transmission delays. Wireless communications can introduce cybersecurity threats to inter-train communications. This work proposes two resilient control strategies for T2T-CBTC systems to mitigate the effects of jamming. Both strategies are based on multi-agent deep reinforcement learning and aim to control trains’ operations under jamming attacks, allowing them to continue operating safely instead of applying emergency braking. One strategy is based on the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm, and the other is based on the Multi-Agent Twin Delayed Deep Deterministic Policy Gradient (MATD3) algorithm. The strategies are implemented and compared with an existing strategy based on MADDPG. The experimental results indicate that the proposed MADDPG-based strategy shortens the convergence time by 32% to 42%, while the MATD3-based strategy achieves a reduction of 40% to 48%, compared to the baseline.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".