# Proof-of-Learning with Incentive Security

arXiv: https://arxiv.org/abs/2404.09005 · HTML: https://mlsanity.com/paper/2404.09005/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 79 references that are in the map.
- First posted on arXiv 13 Apr 2024.

## Builds on (most cited first, 21 of 21)

- [GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection](https://mlsanity.com/paper/2403.03507/) (2024)
- [Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates](https://mlsanity.com/paper/2402.18540/) (2024)
- [Proof-of-Learning: Definitions and Practice](https://mlsanity.com/paper/2103.05633/) (2021)
- [IPFS - Content Addressed, Versioned, P2P File System](https://mlsanity.com/paper/1407.3561/) (2014)
- [Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection](https://mlsanity.com/paper/1802.03041/) (2018)
- [opML: Optimistic Machine Learning on Blockchain](https://mlsanity.com/paper/2401.17555/) (2024)
- ["Adversarial Examples" for Proof-of-Learning](https://mlsanity.com/paper/2108.09454/) (2021)
- [Truthful Data Acquisition via Peer Prediction](https://mlsanity.com/paper/2006.03992/) (2020)
- [Proof-of-Learning is Currently More Broken Than You Think](https://mlsanity.com/paper/2208.03567/) (2022)
- [Coin.AI: A Proof-of-Useful-Work Scheme for Blockchain-based Distributed Deep Learning](https://mlsanity.com/paper/1903.09800/) (2019)
- [A scalable verification solution for blockchains](https://mlsanity.com/paper/1908.04756/) (2019)
- [Compounding of Wealth in Proof-of-Stake Cryptocurrencies](https://mlsanity.com/paper/1809.07468/) (2018)
- [Layer 2 Blockchain Scaling: a Survey](https://mlsanity.com/paper/2107.10881/) (2021)
- [Foundations of Transaction Fee Mechanism Design](https://mlsanity.com/paper/2111.03151/) (2021)
- [Coinami: A Cryptocurrency with DNA Sequence Alignment as Proof-of-work](https://mlsanity.com/paper/1602.03031/) (2016)
- [Proof-of-Stake Longest Chain Protocols: Security vs Predictability](https://mlsanity.com/paper/1910.02218/) (2019)
- [An Uncertainty- and Collusion-Proof Voting Consensus Mechanism in Blockchain](https://mlsanity.com/paper/1912.11620/) (2019)
- [Challenges of Proof-of-Useful-Work (PoUW)](https://mlsanity.com/paper/2209.03865/) (2022)
- [Bitcoin's Carbon Footprint Revisited: Proof of Work Mining for Renewable Energy Expansion](https://mlsanity.com/paper/2304.04578/) (2023)
- [Crowdsourcing Work as Mining: A Decentralized Computation and Storage Paradigm](https://mlsanity.com/paper/2211.06669/) (2022)
- [BAR Nash Equilibrium and Application to Blockchain Design](https://mlsanity.com/paper/2401.16856/) (2024)

## Built on by (most cited first, 4 of 4)

- [Verifiable Fine-Tuning for LLMs: Zero-Knowledge Training Proofs Bound to Data Provenance and Policy](https://mlsanity.com/paper/2510.16830/) (2025)
- [TAO: Tolerance-Aware Optimistic Verification for Floating-Point Neural Networks](https://mlsanity.com/paper/2510.16028/) (2025)
- [PoLO: Proof-of-Learning and Proof-of-Ownership at Once with Chained Watermarking](https://mlsanity.com/paper/2505.12296/) (2025)
- [SEDULity: A Proof-of-Learning Framework for Distributed and Secure Blockchains with Efficient Useful Work](https://mlsanity.com/paper/2512.13666/) (2025)

## Abstract (arXiv)

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, and also improves the computational overhead from Theta(1) to O(fraclog EE). 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.