Longitudinal federated learning backdoor defense method based on neuron activation value clustering

Abstract

The invention discloses a longitudinal federated learning backdoor defense method based on neuron activation value clustering. The method comprises the following steps: constructing a longitudinal federated recommendation system comprising a plurality of participants and collaborators; and federated learning: after obtaining a constructed commodity guiding link corresponding to the aggregation embedding representation, the collaboration party classifies the commodity guiding link to effectively screen out a commodity guiding link with potential backdoor attack, and repairs the commodity guiding link with the backdoor attack by using a clustering result. The back door attack commodity sample is guided to learn towards a correct prediction direction, so that the commodity sample of a participant does not need to be obtained, and the repaired commodity recommendation model can defend the back door attack; and the joint embedded representation with the same ID as the aggregation embedded representation of the backdoor attack is filtered or attacked and repaired, so that the parameter optimization of the aggregation embedded representation of the backdoor attack on the commodity recommendation model is prevented or improved, and the defense capability of the commodity recommendation model on the backdoor attack is improved.

Description

Technical field [0001] The present invention belongs to the provision of privacy safety technology, which specifically relates to a longitudinal federal learning latte defense method based on neuronal activation value clustering. Background technique [0002] Deep learning excellent performance in complex and varied recommended tasks, which makes it gets large-scale applications and deployments in the commodity recommendation system in real scenes. Product recommendation systems constructed in deep learning have further improved their performance than traditional commodity recommendations, which is mainly due to rich computing resources and sufficient calculation data. However, in recent years, some countries and regions have issued data privacy protection regulations to limit the large-scale collection of commercial data, which brings great challenges to deep learning products recommended systems, and coming to enterprises. Data is island phenomenon. [0003] The commercial reco...

AI Technical Summary

Problems solved by technology

However, these two technologies are not suitable for product recommendation systems to defend against the threat of backdoor attacks. The differential privacy technology makes the accuracy of product recommendation tasks drop sharply by adding random noise, and cannot balance the performance of backdoor defense and recommendation task performance.

Gradient sparseness cannot defend the active party of the vertical federated recommendation system from backdoor attacks, mainly because the active party launches backdoor attacks that do not depend on the gradient information of the model

Images