To protect participants’ confidentiality, blockchains can be outfitted with anonymization methods. Observations of the underlying network traffic can identify the author of a transaction request, although these mechanisms often only consider the abstraction layer of blockchains. Previous systems either give topological confidentiality that may be compromised by an attacker in control of a large number of nodes, or provide strong cryptographic confidentiality but are so inefficient as to be practically unusable. In addition, there is no flexible mechanism to swap confidentiality for efficiency in order to accommodate practical demands. We propose a novel approach, the neural fairness protocol, which is a blockchain-based distributed ledger secured using neural networks and machine learning algorithms, enabling permissionless participation in the process of transition validation while concurrently providing strong assurance about the correct functioning of the entire network. Using cryptography and a custom implementation of elliptic curves, the protocol is designed to ensure the confidentiality of each transaction phase and peer-to-peer data exchange.