Research Review on the Application of Homomorphic Encryption in Database Privacy Protection

Ma, Yong; Zhao, Jiale; Li, Kangshun; Cao, Yuanlong; Chen, Huyuan; Zhang, Youcheng

doi:10.4018/ijcini.287600

Cited by 4 publications

(2 citation statements)

References 101 publications

(63 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The calculation formula is shown in (5). PSNR indicates the degree of distortion of the image containing the watermark, and a smaller value means a greater degree of distortion of the original image; the calculation formula is shown in Equation (6).…”

Section: Performance Indexmentioning

confidence: 99%

“…By embedding and extracting the watermark in the ciphertext domain, the information carried by the carrier image will be effectively hidden, significantly improving the carrier image's security. Moreover, homomorphic encryption can safely hand over the encrypted carrier image and watermark to a third party for processing, so there is no need to worry about security risks such as information theft and alteration [6]. The zero watermarking technique is implemented by taking advantage of the vital resources of third parties.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Encrypted Watermarking Algorithm for Medical Images Based on DCT and Improved DarkNet53

Liu

Bhatti

et al. 2023

Electronics

View full text Add to dashboard Cite

To solve the problem of robustness of encrypted medical image watermarking algorithms, a zero watermarking algorithm based on the discrete cosine transform (DCT) and an improved DarkNet53 convolutional neural network is proposed. The algorithm targets medical images in the encrypted domain. In this algorithm, DCT is performed on the encrypted medical image to extract 32-bit features as feature 1. DarkNet53, a pre-trained network, was chosen for migration learning for the network model. The network uses a fully connected layer and a regression layer instead of the original Softmax layer and classification layer, changing the original classification network into a regression network with an output of 128. With these transformations, 128-bit features can be extracted from encrypted medical images by this network, and then DCT is performed to extract 32-bit features as feature 2. The fusion of features 1 and 2 can effectively improve the robustness of the algorithm. The experimental results show that the algorithm can accurately distinguish different encrypted medical images and can effectively restore the original information from the encrypted watermarked information under traditional and geometric attacks. Compared with other algorithms, the proposed method demonstrates better robustness and invisibility.

show abstract

Section: Performance Indexmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%