SEDULity: A Proof-of-Learning Framework for Distributed and Secure Blockchains with Efficient Useful Work

2025-12-15

AI Summary

Proof-of-Work (PoW) consensus mechanisms incur substantial energy waste, while existing Proof-of-Learning (PoL) schemes suffer from trade-offs among security, decentralization, and efficiency. Method: This paper proposes a blockchain-oriented Proof-of-Learning framework featuring (i) a templated block-embedded training workflow and (ii) a computationally hard-to-solve yet easy-to-verify “useful function” design, enabling extensibility across diverse machine learning tasks; it further introduces a verifiably honest incentive mechanism grounded in game-theoretic modeling and cryptographic verification. Contribution/Results: We formally prove that rational miners are strictly incentivized to perform honest model training. Experiments demonstrate that the framework significantly improves training efficiency and reduces verification overhead, while preserving strong decentralization guarantees and provable security against adversarial behavior.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Multiagent Systems: Mechanism Design
• Search and Optimization: Learning to Search

Application Category

• Security and Privacy: Blockchains and distributed ledgers
• Economics, Online Markets and Human Computation: Economic aspects of blockchain and cryptocurrencies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The security and decentralization of Proof-of-Work (PoW) have been well-tested in existing blockchain systems. However, its tremendous energy waste has raised concerns about sustainability. Proof-of-Useful-Work (PoUW) aims to redirect the meaningless computation to meaningful tasks such as solving machine learning (ML) problems, giving rise to the branch of Proof-of-Learning (PoL). While previous studies have proposed various PoLs, they all, to some degree, suffer from security, decentralization, or efficiency issues. In this paper, we propose a PoL framework that trains ML models efficiently while maintaining blockchain security in a fully distributed manner. We name the framework SEDULity, which stands for a Secure, Efficient, Distributed, and Useful Learning-based blockchain system. Specifically, we encode the template block into the training process and design a useful function that is difficult to solve but relatively easy to verify, as a substitute for the PoW puzzle. We show that our framework is distributed, secure, and efficiently trains ML models. We further demonstrate that the proposed PoL framework can be extended to other types of useful work and design an incentive mechanism to incentivize task verification. We show theoretically that a rational miner is incentivized to train fully honestly with well-designed system parameters. Finally, we present simulation results to demonstrate the performance of our framework and validate our analysis.

Problem

• Addresses energy waste in Proof-of-Work blockchains by redirecting computation to machine learning tasks.
• Ensures blockchain security and decentralization while efficiently training distributed ML models.
• Designs a verifiable useful function as a sustainable alternative to traditional PoW puzzles.

Innovation

• Secure distributed blockchain using Proof-of-Learning
• Encoding block template into ML training process
• Designing verifiable useful function replacing PoW puzzle