HP_FLAP: homomorphic and polymorphic federated learning aggregation of parameters framework
Bibliographic record
Abstract
Abstract Protecting user privacy is essential in machine learning research, especially in the context of data collection. Federated learning (FL), which trains models across decentralized devices without sharing raw data, has emerged as a promising solution. However, FL is still vulnerable to security threats, including inference attacks, which have been underexplored in comparison to poisoning and backdoor attacks that have received more attention in existing research. To address these vulnerabilities, this paper proposes a novel aggregation framework called homomorphic and polymorphic federated learning aggregation of parameters (HP_FLAP). HP_FLAP integrates both homomorphic and polymorphic encryption to enhance the security and privacy of FL. Homomorphic encryption allows the server to perform aggregation on encrypted parameters without decrypting them, ensuring that sensitive information is protected during the aggregation process. Polymorphic encryption further strengthens security by using different encryption keys for each set of parameters, mitigating the risk of system-wide compromise in case a key is leaked. This dual encryption approach effectively counters inference attacks while maintaining robust protections against other security threats. The framework is evaluated using multiple models, including logistic regression, Gaussian Naive Bayes, Stochastic Gradient Descent, and Multi-Layer Perceptron, demonstrating HP_FLAP’s ability to enhance both security and privacy in FL environments.
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 | 0.005 | 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 | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| 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".