Learning in the Air: Secure Federated Learning for UAV-Assisted Crowdsensing
Bibliographic record
Abstract
Unmanned aerial vehicles (UAVs) combined with artificial intelligence (AI) have opened a revolutionized way for mobile crowdsensing (MCS). Conventional AI models, built on aggregation of UAVs' sensing data (typically contain private and sensitive user information), may arise severe privacy and data misuse concerns. Federated learning, as a promising distributed AI paradigm, has opened up possibilities for UAVs to collaboratively train a shared global model without revealing their local sensing data. However, there still exist potential security and privacy threats for UAV-assisted crowdsensing with federated learning due to vulnerability of central curator, unreliable contribution recording, and low-quality shared local models. In this paper, we propose SFAC, a secure federated learning framework for UAV-assisted MCS. Specifically, we first introduce a blockchain-based collaborative learning architecture for UAVs to securely exchange local model updates and verify contributions without the central curator. Then, by applying local differential privacy, we design a privacy-preserving algorithm to protect UAVs' privacy of updated local models with desirable learning accuracy. Furthermore, a two-tier reinforcement learning-based incentive mechanism is exploited to promote UAVs' high-quality model sharing when explicit knowledge of network parameters are not available in practice. Extensive simulations are conducted, and the results demonstrate that the proposed SFAC can effectively improve utilities for UAVs, promote high-quality model sharing, and ensure privacy protection in federated learning, compared with existing schemes.
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 | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.003 |
| 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".