Robust and Secure Multi-User STAR-RIS-Aided Communications: Optimization Versus Machine Learning
Bibliographic record
Abstract
This paper investigates simultaneous transmitting and reflecting reconfigurable intelligent surface (STAR-RIS)-assisted multi-user downlink (dl) communications with a primary focus on maximizing information secrecy by considering the channel state information (CSI) error. Acquiring perfect CSI is particularly challenging due to the unavailability of radio frequency chains at the STAR-RIS, the inherent impact of noise and interference on the CSI estimation, as well as non-collaborative nature of the eavesdroppers. In particular, we tackle the worst-case robust beamforming design problem to maximize the sum secrecy rate of the system while considering transmit power limitations, quality of service requirements, and practical constraints on the STAR-RIS phase shifter array. To tackle the resulting non-convex problem, we employ the S-procedure as an initial step to approximate semi-infinite inequality constraints. Subsequently, we leverage the alternating optimization with a line search framework to update the precoder and phase shift matrix iteratively. Furthermore, we extend our solution to address the non-convexity by leveraging a deep reinforcement learning (DRL) multi-agent (MA) framework based on Markov decision process. We also analyze practical phase shifts and the effect of direct links to showcase the practicality of our approach. Simulation results confirm STAR-RIS’s significant performance edge, exhibiting approximately 27.1% higher secrecy in conventional optimization and around 35.4% in the MA-DRL context compared over the conventional RIS. Moreover, our proposed MA-DRL approach surpasses single-agent schemes by about 8.6% in the case of proximal policy optimization and 19.9% in the case of deep deterministic policy gradient, emphasizing the benefits of the MA framework with STAR-RIS.
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 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 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".