A Privacy-Preserving and Trustable Multi-agent Learning Framework

TL;DR

This paper introduces PT-DL, a decentralized multi-agent learning framework that combines differential privacy and blockchain technology to ensure privacy and trustworthiness, resilient against collusion and malicious agents.

Contribution

It proposes a novel framework integrating differential privacy and Ethereum smart contracts for secure, trustable distributed learning, addressing privacy and malicious behavior challenges.

Findings

Resilient up to 50% collusion attacks with high probability.

Effective privacy protection demonstrated on multiple classification tasks.

Enhanced trustability through blockchain-based smart contracts.

Abstract

Distributed multi-agent learning enables agents to cooperatively train a model without requiring to share their datasets. While this setting ensures some level of privacy, it has been shown that, even when data is not directly shared, the training process is vulnerable to privacy attacks including data reconstruction and model inversion attacks. Additionally, malicious agents that train on inverted labels or random data, may arbitrarily weaken the accuracy of the global model. This paper addresses these challenges and presents Privacy-preserving and trustable Distributed Learning (PT-DL), a fully decentralized framework that relies on Differential Privacy to guarantee strong privacy protections of the agents' data, and Ethereum smart contracts to ensure trustability. The paper shows that PT-DL is resilient up to a 50% collusion attack, with high probability, in a malicious trust model and the experimental evaluation illustrates the benefits of the proposed model as a privacy-preserving and trustable distributed multi-agent learning system on several classification tasks.