AP2FL: Auditable Privacy-Preserving Federated Learning Framework for Electronics in Healthcare
Bibliographic record
Abstract
The growing application of machine learning (ML) techniques in healthcare has led to increased interest in federated learning (FL), which enables the secure and private training of robust ML models. However, conventional FL methods often fall short of providing adequate privacy protection and face challenges in handling non-independent and identically distributed (Non-IID) training data. These shortcomings are of significant concern when employing FL in electronic devices in healthcare. To address these issues, we propose an Auditable Privacy-Preserving Federated Learning (AP2FL) model tailored for electronics in healthcare settings. By leveraging Trusted Execution Environments (TEEs), AP2FL ensures secure training and aggregation processes on both client and server sides, effectively mitigating data leakage risks. To manage Non-IID data within the proposed framework, we incorporate the Active Personalized Federated Learning (ActPerFL) model and Batch Normalization (BN) techniques to consolidate user updates and identify data similarities. Additionally, we introduce an auditing mechanism in AP2FL that reveals the contribution of each client to the FL process, facilitating the updating of the global model following diverse data types and distributions. In other words, it ensures the FL process’s integrity, transparency, fairness, and robustness. Our results demonstrate that the proposed AP2FL model outperforms existing methods in accuracy and effectively eliminates privacy leakage.
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 | 0.004 | 0.008 |
| 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 | 0.002 | 0.004 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".