Differential privacy federal modeling method and device for resisting inference attack of semi-honest server

Abstract

The invention provides a differential privacy federated modeling method and device for resisting inference attack of a semi-honest server. The method comprises the following steps: initializing a global model; the semi-honesty central server selects a plurality of data participants to participate in the federation training according to a preset probability; downloading the global model by the selected data participant, and performing elastic fusion on the local model trained in the previous round and the global model to obtain a local model after elastic fusion; the selected data participant performs local private training on the elastically fused local model by using local data to obtain a local model after noise disturbance, and then sends the local model to a semi-honest central server; and the semi-honesty central server aggregates the local models after noise disturbance to obtain a global model of disturbance. According to the method, the robustness in the joint modeling process can be improved, and the precision of the model can also be improved.

Description

technical field [0001] The invention relates to the technical field of privacy-enhanced federated learning for multi-party joint deep learning modeling, in particular to a differential privacy federated modeling method and device for resisting semi-honest server inference attacks. Background technique [0002] Data has become a basic production factor for information circulation and value transfer. How to promote the circulation and sharing of data on the premise of protecting privacy is a major challenge currently facing. Federated learning is a new paradigm of machine learning and deep learning model training. It keeps model training and data storage at the edge of the distributed network. Its privacy protection ability shows its application value in many business scenarios. It enables all participants to join forces without sharing data resources, that is, to establish a sharing model without the need to share data locally, and effectively solve the problems of data priva...

AI Technical Summary

Problems solved by technology

[0005] The present invention proposes a differential privacy federated modeling method and device for resisting semi-honest server inference attacks, to solve or at least partially solve the technical problems in the prior art that the inference attacks cannot be resisted and the model accuracy is not high due to differential privacy

Images