Privacy protection-based user authenticated outsourcing image denoising method

Abstract

The invention relates to a privacy protection-based user authenticated outsourcing image denoising method. The method comprises the following steps that: a trusted third party TTP allocates related keys to a content owner CO, an authorized user AU and two edge computing servers ES1 and ES2; the CO firstly uses a secret key distributed by the TTP to encrypt a noisy image, and sends the encrypted image to the first edge computing server ES1; the second edge computing server ES2 assists the first edge computing server ES1 to perform ciphertext image denoising, and a result obtained through calculation is sent to the first edge computing server ES1; and the AU makes an image use request to the corresponding CO, obtains the corresponding denoised ciphertext image from the first edge computing server ES1, and authorizes the user AU to decrypt and recover the required plaintext denoised image with the help of the private key of the AU. According to the invention, the image denoising service is provided while the user privacy data security is ensured; and moreover, the local calculation and communication overhead of the user is reduced, and the ciphertext denoising effect is almost equal to the plaintext domain performance.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a user-authenticable outsourced image denoising method based on privacy protection. Background technique [0002] At present, computer vision technology has been widely used in image classification, object detection, semantic segmentation and other fields. These fields generally have certain requirements for image quality, but in reality, the digital images obtained by the imaging equipment itself or many external environment interferences are often noisy. If these noisy images are directly used as samples for research, it may be difficult have a certain negative impact on the research results. Therefore, before image processing, it is often necessary to perform a denoising preprocessing operation on the sample image to obtain higher quality sample data. [0003] In recent years, with the popularization of mobile imaging devices such as smart phones and digital cameras...

AI Technical Summary

Problems solved by technology

However, in the new scheme, the JL transformation still needs to be performed by the client, and the denoising process requires the user to interact with the two cloud servers

[0005] The above three types of ciphertext denoising schemes are all based on cloud servers (see figure 1 ), easily lead to processing time delay and high demand for network bandwidth, affecting user experience

In addition, the existing scheme does not consider the issue of outsourcing authentication for users to perform authorization and revocation operations from the perspective of system practicability

Currently, the field still lacks a viable approach that supports privacy-preserving low-latency and user-authenticable outsourced image denoising schemes.

Images