A Novel Secure Split Federated Semantic Learning Framework and its Optimization for Digital Twin Network Evolution
Bibliographic record
Abstract
This paper introduces a novel secure split federated semantic learning (SFsL) framework to facilitate the maintenance and evolution of digital twin networks (DTNs). Efficiently updating and evolving DTNs generally involves several critical processes: semantic extraction and transmission for physical-to-virtual synchronization, virtual model transformation and verification, and ensuring the security and privacy of physical entity data. While conventional semantic communication frameworks can effectively address semantic extraction and transmission, the complexities of virtual model transformation, verification, and data security demand a more comprehensive approach. To address these challenges, the proposed SFsL framework integrates split federated learning with task-oriented secure semantic communication schemes. In addition, it incorporates a token-based semantic defence method to distinguish between adversarial and authentic semantic data and an asynchronous secure model aggregation mechanism to enhance data-sharing efficiency. The system reliability is then formulated as a stochastic optimization problem, aiming to minimize cost complexity while maintaining high accuracy during periodic model aggregation. Evaluation results, obtained using performance metrics such as privacy loss, experienced loss, accuracy, cost and reliability, demonstrate that the SFsL framework outperforms other commonly adopted security and privacy schemes, offering improved efficiency towards the maintenance and evolution of such dynamic systems. This highlights the capability of SFsL to enable adaptive, efficient and reliable network evolutions when deployed in practical DTNs with dynamic resource constraints.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 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 | 0.002 | 0.002 |
| 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".