基于DC-Nets和秘密共享的安全聚合协议,用于分散的联合学习
Diogo Pereira1, Paulo Ricardo Reis1, Fábio Borges1
1National Laboratory for Scientific Computing, Petrópolis 25651-075, RJ, Brazil.
Sensors (Basel, Switzerland)
|February 24, 2024
概括
本研究介绍了一种安全的聚合协议,用于使用多秘密共享和餐饮密码学家网络进行去中心化联合学习 (FL). 新协议在没有中央服务器的情况下增强了数据隐私,实现了与传统FL方法相似的结果.
科学领域:
- 计算机科学 计算机科学
- 机器学习 机器学习
- 密码学 密码学 密码学 密码学
背景情况:
- 大数据生成需要机器学习模型培训.
- 培训中的敏感数据带来隐私风险和监管挑战.
- 联合学习 (FL) 提供了一种保护隐私的方法,但仍然容易受到数据重建攻击.
研究的目的:
- 为分散式联合学习 (DFL) 提出一个安全的聚合协议.
- 通过消除对中央服务器的需求,增强FL的数据隐私.
- 为现有的FL聚合方法提供一个保护隐私的替代方案.
主要方法:
- 开发了一个安全的聚合协议,将多密共享 (MSS) 与餐饮密码学家网络 (DCN) 结合起来.
- 在使用MNIST手写数字数据集的模拟中实施和验证了协议.
- 将协议的性能与标准联邦学习与 FedAvg 协议进行了比较.
主要成果:
- 拟议的DFL协议实现了与FedAvg.相似的准确性.
- 该协议显著增强了用户数据的隐私,防止潜在的攻击.
- 定时性能高效,避免了与同型加密相关的重大开销.
结论:
- 新的DFL协议在机器学习模型训练期间有效保护敏感数据.
- MSS和DCN的结合提供了一个强大的,高效的隐私保护解决方案.
- 这种方法推进了安全的去中心化机器学习实践.
相关概念视频
Fast Decoupled and DC Powerflow
961
The fast decoupled power flow method addresses contingencies in power system operations, such as generator outages or transmission line failures. This method provides quick power flow solutions, essential for real-time system adjustments. Fast decoupled power flow algorithms simplify the Jacobian matrix by neglecting certain elements, leading to two sets of decoupled equations:
961
Associative Learning
2.1K
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Classical conditioning, also known...
2.1K


