NN-QuPiD Attack: Neural Network-Based Privacy Quantification Model for Private Information Retrieval Protocols

Web search engines usually keep users’ profiles for multiple purposes, such as result ranking and relevancy, market research, and targeted advertisements. However, user web search history may contain sensitive and private information about the user, such as health condition, personal interests, and...

Full description

Saved in:
Bibliographic Details
Main Authors: Rafiullah Khan, Mohib Ullah, Atif Khan, Muhammad Irfan Uddin, Maha Al-Yahya
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2021/6651662
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850211066001227776
author Rafiullah Khan
Mohib Ullah
Atif Khan
Muhammad Irfan Uddin
Maha Al-Yahya
author_facet Rafiullah Khan
Mohib Ullah
Atif Khan
Muhammad Irfan Uddin
Maha Al-Yahya
author_sort Rafiullah Khan
collection DOAJ
description Web search engines usually keep users’ profiles for multiple purposes, such as result ranking and relevancy, market research, and targeted advertisements. However, user web search history may contain sensitive and private information about the user, such as health condition, personal interests, and affiliations that may infringe users’ privacy since a user’s identity may be exposed and misused by third parties. Numerous techniques are available to address privacy infringement, including Private Information Retrieval (PIR) protocols that use peer nodes to preserve privacy. Previously, we have proved that PIR protocols are vulnerable to the QuPiD Attack. In this research, we proposed NN-QuPiD Attack, an improved version of QuPiD Attack that uses an Artificial Neural Network (RNN) based model to associate queries with their original users. The results show that the NN-QuPiD Attack gave 0.512 Recall with the Precision of 0.923, whereas simple QuPiD Attack gave 0.49 Recall with the Precision of 0.934 with the same data.
format Article
id doaj-art-897b3b43fce7466693f276a72a8a08c1
institution OA Journals
issn 1076-2787
1099-0526
language English
publishDate 2021-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-897b3b43fce7466693f276a72a8a08c12025-08-20T02:09:38ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/66516626651662NN-QuPiD Attack: Neural Network-Based Privacy Quantification Model for Private Information Retrieval ProtocolsRafiullah Khan0Mohib Ullah1Atif Khan2Muhammad Irfan Uddin3Maha Al-Yahya4Institute of Computer Science & Information Technology, The University of Agriculture, Peshawar, PakistanInstitute of Computer Science & Information Technology, The University of Agriculture, Peshawar, PakistanDepartment of Computer Science, Islamia College Peshawar, Peshawar, KP, PakistanInstitute of Computing, Kohat University of Science and Technology, Kohat, PakistanDepartment of Information Technology, College of Computer and Information Sciences, King Saud University, P. O. Box 145111, 4545 Riyadh, Saudi ArabiaWeb search engines usually keep users’ profiles for multiple purposes, such as result ranking and relevancy, market research, and targeted advertisements. However, user web search history may contain sensitive and private information about the user, such as health condition, personal interests, and affiliations that may infringe users’ privacy since a user’s identity may be exposed and misused by third parties. Numerous techniques are available to address privacy infringement, including Private Information Retrieval (PIR) protocols that use peer nodes to preserve privacy. Previously, we have proved that PIR protocols are vulnerable to the QuPiD Attack. In this research, we proposed NN-QuPiD Attack, an improved version of QuPiD Attack that uses an Artificial Neural Network (RNN) based model to associate queries with their original users. The results show that the NN-QuPiD Attack gave 0.512 Recall with the Precision of 0.923, whereas simple QuPiD Attack gave 0.49 Recall with the Precision of 0.934 with the same data.http://dx.doi.org/10.1155/2021/6651662
spellingShingle Rafiullah Khan
Mohib Ullah
Atif Khan
Muhammad Irfan Uddin
Maha Al-Yahya
NN-QuPiD Attack: Neural Network-Based Privacy Quantification Model for Private Information Retrieval Protocols
Complexity
title NN-QuPiD Attack: Neural Network-Based Privacy Quantification Model for Private Information Retrieval Protocols
title_full NN-QuPiD Attack: Neural Network-Based Privacy Quantification Model for Private Information Retrieval Protocols
title_fullStr NN-QuPiD Attack: Neural Network-Based Privacy Quantification Model for Private Information Retrieval Protocols
title_full_unstemmed NN-QuPiD Attack: Neural Network-Based Privacy Quantification Model for Private Information Retrieval Protocols
title_short NN-QuPiD Attack: Neural Network-Based Privacy Quantification Model for Private Information Retrieval Protocols
title_sort nn qupid attack neural network based privacy quantification model for private information retrieval protocols
url http://dx.doi.org/10.1155/2021/6651662
work_keys_str_mv AT rafiullahkhan nnqupidattackneuralnetworkbasedprivacyquantificationmodelforprivateinformationretrievalprotocols
AT mohibullah nnqupidattackneuralnetworkbasedprivacyquantificationmodelforprivateinformationretrievalprotocols
AT atifkhan nnqupidattackneuralnetworkbasedprivacyquantificationmodelforprivateinformationretrievalprotocols
AT muhammadirfanuddin nnqupidattackneuralnetworkbasedprivacyquantificationmodelforprivateinformationretrievalprotocols
AT mahaalyahya nnqupidattackneuralnetworkbasedprivacyquantificationmodelforprivateinformationretrievalprotocols