差别隐私
计算机科学
稳健性(进化)
趋同(经济学)
推论
噪音(视频)
信息隐私
人为噪声
网络拓扑
分布式计算
收敛速度
信息敏感性
隐私软件
随机过程
发电机(电路理论)
人工智能
噪声测量
数据挖掘
理论计算机科学
数学优化
加速
正多边形
凸函数
机器学习
通信噪声
作者
Luqing Wang,Shaofu Yang,Yong Wan,Wenying Xu,Min-Ling Zhang
标识
DOI:10.1109/tpami.2026.3672569
摘要
Ensuring the privacy of local datasets has emerged as an important concern in decentralized learning. However, the inherent privacy-utility tradeoff remains a fundamental challenge for privacy preserving decentralized algorithms. To address this issue, we introduce Positive-Incentive Noise Generator (PING), a novel mechanism designed to eliminate negative impact of privacy noise on convergence while defending against powerful colluding inference attacks. PING leverages network topologies and lightweight encryption-decryption operations to generate correlated noise. Building upon PING, we propose PP-DPIN, a privacy preserving stochastic algorithm tailored for decentralized learning. By integrating differential privacy and differential information entropy, we provide a comprehensive privacy quantification for PP-DPIN, with at least half nodes achieving arbitrarily strong privacy guarantees. Furthermore, convergence rate of PP-DPIN is established under stochastic convex and nonconvex settings, which characterizes the impact of privacy noise and demonstrates the linear speedup relative to the network size. Experiments on computer vision tasks validate PP-DPIN's superior performance and robustness against attacks compared to state-of-the-art methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI