Toward Secure and Private Federated Learning for IoT using Blockchain
Bibliographic record
Abstract
Recent advances in the Internet of Things (IoT) offer a plethora of new opportunities for several intelligent services and applications. As the IoT connects a massive number of devices, inevitable security threats must be addressed. On the one hand, machine learning (ML), especially federated learning (FL), is proposed as a promising distributed ML paradigm to improve attack detection performance in the IoT network due to its privacy-preserving and lower latency advantages. On the other hand, blockchain is proposed as a decentralized technology to establish a secure and decentralized environment for IoT devices. However,$F$L and blockchain solutions are not well suited for the IoT context that suffers from resource limitations, such as limited communication bandwidth and scarce computing resources of IoT devices. In addition, traditional FL and blockchain solutions are unable to guarantee the reliability of data. In this paper, we present a decentralized FL framework powered by blockchain for security attack protection in IoT systems. In addition, we propose an oracle blockchain network that protects privacy and guarantees data reliability. The oracle blockchain acts as a trusted third party to verify the reliability of data and pattern formation at the network edge. Finally, we will formulate a resource allocation problem to allocate the necessary bandwidth to selected devices meticulously. The goal is to minimize communication between devices in the framework and prioritize devices with reliable behavior.
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 | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.001 | 0.004 |
| Research integrity | 0.001 | 0.002 |
| 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".