Improving Secrecy Capacity in the Face of Eavesdropping in SWIPT CIoT Networks With Actor-Critic DRL
Bibliographic record
Abstract
One of the key enablers of 6th-generation (6G) wireless networks is cognitive radio, offering optimized spectrum utilization, enhanced device intelligence, and improved security. This article investigates secure communication in an energy-harvesting (EH) cognitive Internet of Things (CIoT) network operating over cascaded fading channels. Here, a CIoT transmitter employs an intelligent strategy to allocate time for simultaneous wireless information and power transfer (SWIPT) and transmission power to maximize the secrecy rate. The CIoT receiver operates in full-duplex (FD) mode, receiving confidential messages while simultaneously emitting cooperative jamming signals to disrupt an eavesdropper. We formulate the challenging non-convex optimization problem to maximize secrecy capacity while ensuring spectrum sharing and energy constraints and model the CIoT agent’s decision-making as a model-free Markov decision process (MDP). We then propose a deep reinforcement learning (DRL) approach to determine the optimal strategy for secure transmission and resource allocation. Specifically, we derive the instantaneous secrecy rate and employ a deep deterministic policy gradient (DDPG) algorithm with a lightweight actor-critic architecture to efficiently address dynamic channel occupancy, EH opportunities, and fading conditions. The proposed DDPG algorithm allows the CIoT agent to adapt to dynamic environments, enhance transmission security, and extend network lifetime without prior knowledge. Extensive simulations confirm its convergence and effectiveness in improving secrecy capacity, throughput, and energy efficiency. Moreover, the results attest to its superior performance compared to existing benchmarks.
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 | 0.000 |
| 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) | 0.001 | 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".