FETCH: A cloud-native searchable encryption scheme enabling efficient pattern search on encrypted data within cloud services

2019 ◽  
pp. e4141 ◽  
Author(s):  
Shen-Ming Chung ◽  
Ming-Der Shieh ◽  
Tzi-Cker Chiueh
Keyword(s):  
Pattern Search ◽  
Cloud Services ◽  
Searchable Encryption ◽  
Encryption Scheme ◽  
Encrypted Data

scholarly journals SecureDL: A privacy preserving deep learning model for image recognition over cloud

2021 ◽  
Author(s):  
Vishesh Kumar Tanwar ◽  
Balasubramanian Raman ◽  
Amitesh Singh Rajput ◽  
Rama Bhargava
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Visual Information ◽  
Low Cost ◽  
Number System ◽  
Privacy Preserving ◽  
Cloud Services ◽  
Binary Number ◽  
Encryption Scheme ◽  
Encrypted Data

<div>The key benefits of cloud services, such as low cost, access flexibility, and mobility, have attracted users worldwide to utilize the deep learning algorithms for developing computer vision tasks. Untrusted third parties maintain these cloud servers, and users are always concerned about sharing their confidential data with them. In this paper, we addressed these concerns for by developing SecureDL, a privacy-preserving image recognition model for encrypted data over cloud. Additionally, we proposed a block-based image encryption scheme to protect images’ visual information. The scheme constitutes an order-preserving permutation ordered binary number system and pseudo-random matrices. The encryption scheme is proved to be secure in a probabilistic viewpoint and through various cryptographic attacks. Experiments are performed for several image recognition datasets, and the achieved recognition accuracy for encrypted data is close with non-encrypted data. SecureDL overcomes the storage, and computational overheads occurred in fully-homomorphic and multi-party computations based secure recognition schemes. </div>

scholarly journals SecureDL: A privacy preserving deep learning model for image recognition over cloud

2021 ◽  
Author(s):  
Vishesh Kumar Tanwar ◽  
Balasubramanian Raman ◽  
Amitesh Singh Rajput ◽  
Rama Bhargava
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Visual Information ◽  
Low Cost ◽  
Number System ◽  
Privacy Preserving ◽  
Cloud Services ◽  
Binary Number ◽  
Encryption Scheme ◽  
Encrypted Data

<div>The key benefits of cloud services, such as low cost, access flexibility, and mobility, have attracted users worldwide to utilize the deep learning algorithms for developing computer vision tasks. Untrusted third parties maintain these cloud servers, and users are always concerned about sharing their confidential data with them. In this paper, we addressed these concerns for by developing SecureDL, a privacy-preserving image recognition model for encrypted data over cloud. Additionally, we proposed a block-based image encryption scheme to protect images’ visual information. The scheme constitutes an order-preserving permutation ordered binary number system and pseudo-random matrices. The encryption scheme is proved to be secure in a probabilistic viewpoint and through various cryptographic attacks. Experiments are performed for several image recognition datasets, and the achieved recognition accuracy for encrypted data is close with non-encrypted data. SecureDL overcomes the storage, and computational overheads occurred in fully-homomorphic and multi-party computations based secure recognition schemes. </div>

scholarly journals Text File Privacy on the Cloud Based on Diagonal Fragmentation and Encryption

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Tawfiq Barhoom ◽  
Mahmoud Abu Shawish
Keyword(s):  
Data Privacy ◽  
Cloud Services ◽  
Text File ◽  
Layer Model ◽  
Encrypted Data ◽  
Cloud Server ◽  
Cloud Environments ◽  
Encryption Algorithms ◽  
Well Data ◽  
Encryption Method

Despite the growing reliance on cloud services and software, privacy is somewhat difficult. We store our data on remote servers in cloud environments that are untrusted. If we do not handle the stored data well, data privacy can be violated with no awareness on our part. Although it requires expensive computation, encrypting the data before sending it appears to be a solution to this problem. So far, all known solutions to protect textual files using encryption algorithms fell short of privacy expectations. Thus is because encrypting cannot stand by itself. The encrypted data on the cloud server becomes full file in the hand causing the privacy of this data to be intrusion-prone, thus allowing intruders to access the file data once they can decrypt it. This study aimed to develop an effective cloud confidentiality model based on combining fragmentation and encryption of text files to compensate for reported deficiency in encryption methods. The fragmentation method used the strategy of dividing text files into two triangles through the axis. Whereas the encryption method used the Blowfish algorithm. The research concluded that high confidentiality is achieved by building a multi-layer model: encryption, chunk, and fragmentation of every chunk to prevent intruders from reaching the data even if they were able to decrypt the file. Using the privacy accuracy equation (developed for the purpose in this research), the model achieved accuracy levels of 96% and 90% when using 100 and 200 words in each chunk on small, medium, and large files respectively.

Sign in / Sign up

Export Citation Format

Share Document