A Privacy-Preserving and Trustable Multi-agent Learning Framework
It addresses privacy and trust issues in distributed learning for applications requiring secure collaboration, though it is incremental by combining existing techniques.
The paper tackles vulnerabilities in distributed multi-agent learning to privacy attacks and malicious agents by proposing PT-DL, a decentralized framework using Differential Privacy and Ethereum smart contracts, which resists up to 50% collusion attacks with high probability.
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.