Most concurrent blockchain systems rely heavily on the Proof-of-Work (PoW) or Proof-of-Stake (PoS) mechanisms for decentralized consensus and security assurance. However, the substantial energy expenditure stemming from computationally intensive yet meaningless tasks has raised considerable concerns surrounding traditional PoW approaches, The PoS mechanism, while free of energy consumption, is subject to security and economic issues. Addressing these issues, the paradigm of Proof-of-Useful-Work (PoUW) seeks to employ challenges of practical significance as PoW, thereby imbuing energy consumption with tangible value. While previous efforts in Proof of Learning (PoL) explored the utilization of deep learning model training SGD tasks as PoUW challenges, recent research has revealed its vulnerabilities to adversarial attacks and the theoretical hardness in crafting a byzantine-secure PoL mechanism. In this paper, we introduce the concept of incentive-security that incentivizes rational provers to behave honestly for their best interest, bypassing the existing hardness to design a PoL mechanism with computational efficiency, a provable incentive-security guarantee and controllable difficulty. Particularly, our work is secure against two attacks to the recent work of Jia et al. [2021], and also improves the computational overhead from $\Theta(1)$ to $O(\frac{\log E}{E})$. Furthermore, while most recent research assumes trusted problem providers and verifiers, our design also guarantees frontend incentive-security even when problem providers are untrusted, and verifier incentive-security that bypasses the Verifier's Dilemma. By incorporating ML training into blockchain consensus mechanisms with provable guarantees, our research not only proposes an eco-friendly solution to blockchain systems, but also provides a proposal for a completely decentralized computing power market in the new AI age.

翻译：当前大多数区块链系统严重依赖工作量证明（PoW）或权益证明（PoS）机制来实现去中心化共识与安全保障。然而，由计算密集却无实际意义的任务所导致的巨大能源消耗，已引发对传统PoW方法的广泛担忧。PoS机制虽无能耗问题，却面临安全性与经济性方面的挑战。为解决这些问题，有用工作量证明（PoUW）范式试图将具有实际意义的挑战作为PoW任务，从而赋予能源消耗以切实价值。尽管先前学习证明（PoL）的研究探索了将深度学习模型训练SGD任务作为PoUW挑战，但近期研究揭示了其易受对抗攻击的脆弱性，以及构建拜占庭安全PoL机制在理论上的困难。本文提出激励安全性的概念，通过激励理性证明者为自身最优利益而保持诚实行为，从而绕过现有理论障碍，设计出具有计算高效性、可证明激励安全性保证及难度可控性的PoL机制。特别地，我们的工作能够抵御针对Jia等人[2021]近期研究的两种攻击，并将计算开销从$\Theta(1)$改进至$O(\frac{\log E}{E})$。此外，尽管近期多数研究假设问题提供者与验证者可信，我们的设计即使在不信任问题提供者的情况下仍能保证前端激励安全性，并通过规避验证者困境来实现验证者激励安全性。通过将机器学习训练融入具有可证明保证的区块链共识机制，本研究不仅为区块链系统提出了环保解决方案，更为新人工智能时代完全去中心化的算力市场提供了可行方案。