Proof-of-Useful-Work as Dual-Purpose Mechanism for Blockchain and AI: Blockchain Consensus that Enables Privacy Preserving Data Mining
This addresses the inefficiency of blockchain consensus for the broader AI and blockchain communities, offering a novel integration rather than an incremental improvement.
The paper tackles the problem of energy waste in blockchain proof-of-work consensus by proposing a hybrid scheme that redirects computational resources to optimize machine learning models, achieving a dual-purpose mechanism for blockchain security and AI utility.
Blockchains rely on a consensus among participants to achieve decentralization and security. However, reaching consensus in an online, digital world where identities are not tied to physical users is a challenging problem. Proof-of-work provides a solution by linking representation to a valuable, physical resource. While this has worked well, it uses a tremendous amount of specialized hardware and energy, with no utility beyond blockchain security. Here, we propose an alternative consensus scheme that directs the computational resources to the optimization of machine learning (ML) models, a task with more general utility. This is achieved by a hybrid consensus scheme relying on three parties: data providers, miners, and a committee. The data provider makes data available and provides payment in return for the best model, miners compete about the payment and access to the committee by producing ML optimized models, and the committee controls the ML competition.