Privacy-Preserving and Accountable Multi-agent Learning
Privacy-Preserving and Accountable Multi-agent Learning
复制标题
DOI：
10.5555/3463952.3464174
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Anudit Nagar;Cuong Tran;Ferdinando Fioretto
中科院分区：
文献类型：
--
作者：
Anudit Nagar;Cuong Tran;Ferdinando Fioretto
分布式多智能体学习使智能体能够合作训练模型，而无需共享它们的数据集。虽然这种设置确保了一定程度的隐私，但已经表明，即使数据不直接共享，训练过程也容易受到隐私攻击，包括数据重建和模型反演攻击。此外，在反向标签或随机数据上训练的恶意代理可能会任意削弱全局模型的准确性。本文解决了这些挑战，并提出了隐私保护和可问责分布式学习（PA-DL），这是一个完全分散的框架，依赖于差分隐私来保证代理数据的强大隐私保护，以及以太坊智能合约来确保问责制。
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 Accountable Distributed Learning (PA-DL), a fully decentralized framework that relies on Differential Privacy to guarantee strong privacy protection of the agents data, and Ethereum smart contracts to ensure accountability.