Unlock instant, AI-driven research and patent intelligence for your innovation.

A data aggregation signature system and method against malicious transmission data attack

A technology for data transmission and data aggregation, applied in transmission systems, digital transmission systems, digital data protection, etc., can solve problems such as difficulties, time-consuming, and low practical effects, and achieve high practicability, high privacy protection and security Effect

Active Publication Date: 2022-05-17
HUBEI UNIV OF TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The existing scheme can effectively prevent both users from obtaining the data of the other party, but in the case of encryption, it is calculated that θ=(X T X) -1 x T Y is obviously very difficult
Computing on the ciphertext (X T X) -1 It takes a lot of time, and the practical effect of this method is not high
And in the process of data transmission by the user, the adversary can cause the training to fail by destroying the data
[0006] Existing schemes for two-party privacy-preserving linear regression are not resistant to adversary attacks, and are not practical due to excessive time consumption

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A data aggregation signature system and method against malicious transmission data attack
  • A data aggregation signature system and method against malicious transmission data attack
  • A data aggregation signature system and method against malicious transmission data attack

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the implementation examples described here are only used to illustrate and explain the present invention, and are not intended to limit this invention.

[0032] please see figure 1 , the invention provides a data aggregation signature system against malicious transmission data attack. Specifically, it includes User A (User A) and User B (User B).

[0033] User A and user B cooperate to complete the training of the gradient descent model based on our scheme.

[0034] please see figure 2 and image 3 , a kind of anti-malicious transmission data attack data aggregation signature method provided by the present invention, comprises the following steps:

[0035] Step 1: Generation of system parameters and veri...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a data aggregation signature system and method against malicious transmission data attack. The system includes User A (User A) and User B (User B). User A and user B cooperate to complete the training of the gradient descent model based on our scheme. The method includes five parts: generation of system parameters and verification keys, two-party cooperative update θ, aggregated signatures, set verification, and elimination of redundant parameters; the invention can ensure that user privacy is not leaked under malicious attacks.

Description

technical field [0001] The invention belongs to the technical field of secure multi-party computing and the technical field of deep learning for privacy protection, and relates to a model training method for two-party privacy protection; in particular, it relates to an anti-malicious transmission data attack for user data privacy protection against malicious transmission data attacks Data aggregation signature system and method. Background technique [0002] Linear regression model is a typical application model of deep learning. Whether in medicine, agriculture, or the financial industry, regression models have good applications. With the vigorous development of big data, linear regression models have been established. Has been used as a general model for deep learning. Today, linear regression models are used in many fields such as computer vision, speech recognition, disease diagnosis, and other scenarios. For a big company like Baidu, they have enough data to provide...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04L9/08H04L9/32H04L9/40G06F21/62G06F21/64
CPCH04L9/0825H04L9/0869H04L9/3247H04L63/12H04L63/1441G06F21/64G06F21/6245Y02D30/50
Inventor 张明武库汉超张语荻
Owner HUBEI UNIV OF TECH