This paper introduces ZIP-DL, a novel privacy-aware decentralized learning
(DL) algorithm that relies on adding correlated noise to each model update
during the model training process. This technique ensures that the added noise
almost neutralizes itself during the aggregation process due to its
correlation, thus minimizing the impact on model accuracy. In addition, ZIP-DL
does not require multiple communication rounds for noise cancellation,
addressing the common trade-off between privacy protection and communication
overhead. We provide theoretical guarantees for both convergence speed and
privacy guarantees, thereby making ZIP-DL applicable to practical scenarios.
Our extensive experimental study shows that ZIP-DL achieves the best trade-off
between vulnerability and accuracy. In particular, ZIP-DL (i) reduces the
effectiveness of a linkability attack by up to 52 points compared to baseline
DL, and (ii) achieves up to 37 more accuracy points for the same vulnerability
under membership inference attacks against a privacy-preserving competitor

介绍了 ZIP-DL 这一创新的隐私保护分散式学习算法，通过在模型训练过程中添加相关噪声的方法来确保噪声在聚合过程中几乎自动中和，最小化对模型准确性的影响；ZIP-DL 不需要多次通信来进行噪声抵消，解决了隐私保护和通信开销之间的常见权衡问题，并提供了收敛速度和隐私保证的理论保证，从而使其适用于实际场景；详尽的实验研究表明，ZIP-DL 在漏洞性和准确性之间取得了最佳平衡，特别是相比基线 DL，(i) 将可链接性攻击的有效性降低了最多 52 个百分点，并且 (ii) 在面对针对隐私保护竞争对手的成员推断攻击时，相同漏洞下的准确性提高了最多 37 个百分点。