TraCemop: Toward Federated Learning With Traceable Contribution Evaluation and Model Ownership Protection
Bibliographic record
Abstract
Federated Learning (FL) allows multiple clients to collaboratively train machine learning models without the need to share their local private data. As a result, it can effectively address the issue of data fragmentation. Nevertheless, insufficient evaluation of individual contributions and the lack of protections for both the intellectual property rights (IPR) of models and client privacy can greatly reduce clients' motivations in federated training. To address these challenges, this paper introduces the Traceable Contribution Evaluation and Model Ownership Protection (TraCemop) framework for federated learning, which allows each client to swiftly assess the contributions of others in each round, with integrated support for the traceability of evaluation results. To safeguard the intellectual property of models, a collective watermark is embedded in the global model. Additionally, a secure mechanism for verifying model ownership is also available in case of disputes. Security analysis indicates that TraCemop is capable of resisting data reconstruction attacks as well as various types of model copyright infringements. Finally, we evaluate the proposed framework using two commonly-used datasets, and the experimental results show a significant improvement in the efficiency of contribution evaluation compared to existing methods. Meanwhile, IPR infringement tests on TraCemop reveal that the proposed framework is resilient against malicious efforts to monopolize model ownership.
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 | 0.016 | 0.035 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.009 |
| Open science | 0.005 | 0.012 |
| Research integrity | 0.003 | 0.004 |
| Insufficient payload (model declined to judge) | 0.002 | 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".