Despite recent progress in enhancing the privacy of federated learning (FL)
via differential privacy (DP), the trade-off of DP between privacy protection
and performance is still underexplored for real-world medical scenario. In this
paper, we propose to optimize the trade-off under the context of client-level
DP, which focuses on privacy during communications. However, FL for medical
imaging involves typically much fewer participants (hospitals) than other
domains (e.g., mobile devices), thus ensuring clients be differentially private
is much more challenging. To tackle this problem, we propose an adaptive
intermediary strategy to improve performance without harming privacy.
Specifically, we theoretically find splitting clients into sub-clients, which
serve as intermediaries between hospitals and the server, can mitigate the
noises introduced by DP without harming privacy. Our proposed approach is
empirically evaluated on both classification and segmentation tasks using two
public datasets, and its effectiveness is demonstrated with significant
performance improvements and comprehensive analytical studies. Code is
available at: this https URL

通过在客户端层面的差分隐私，我们提出了一种适应性中介策略来在不损害隐私的情况下改善性能，通过将客户端分割为子客户端来缓解差分隐私引入的噪音，并使用两个公共数据集进行了实证评估，证明了该方法的有效性和性能改进。

通过自适应中介实现联邦医学成像的客户级差分隐私

Client-Level Differential Privacy via Adaptive Intermediary in Federated  Medical Imaging

In this paper, a possibilistic disjunctive logic programming approach for
modeling uncertain, incomplete and inconsistent information is defined. This
approach introduces the use of possibilistic disjunctive clauses which are able
to capture incomplete information and incomplete states of a knowledge base at
the same time.
By considering a possibilistic logic program as a possibilistic logic theory,
a construction of a possibilistic logic programming semantic based on answer
sets and the proof theory of possibilistic logic is defined. It shows that this
possibilistic semantics for disjunctive logic programs can be characterized by
a fixed-point operator. It is also shown that the suggested possibilistic
semantics can be computed by a resolution algorithm and the consideration of
optimal refutations from a possibilistic logic theory.
In order to manage inconsistent possibilistic logic programs, a preference
criterion between inconsistent possibilistic models is defined; in addition,
the approach of cuts for restoring consistency of an inconsistent possibilistic
knowledge base is adopted. The approach is illustrated in a medical scenario.

定义了一种适用于建模不确定、不完整和不一致信息的可能性析取逻辑编程方法，并介绍了可能性析取子句的使用，该子句能够同时捕捉知识库的不完全信息和不完全状态；同时基于经典答案集语义和可能性逻辑证明理论构建可能性逻辑编程语义，对于不一致可能性逻辑程序的管理，采用偏好标准和切割方法进行篡改，并以医学场景为例进行了说明。