A user sensitive subject protection approach for book search service

Abstract

In a digital library, book search is one of the most important information services. However, with the rapid development of network technologies such as cloud computing, the server‐side of a digital library is becoming more and more untrusted; thus, how to prevent the disclosure of users' book query privacy is causing people's increasingly extensive concern. In this article, we propose to construct a group of plausible fake queries for each user book query to cover up the sensitive subjects behind users' queries. First, we propose a basic framework for the privacy protection in book search, which requires no change to the book search algorithm running on the server‐side, and no compromise to the accuracy of book search. Second, we present a privacy protection model for book search to formulate the constraints that ideal fake queries should satisfy, that is, (i) the feature similarity, which measures the confusion effect of fake queries on users' queries, and (ii) the privacy exposure, which measures the cover‐up effect of fake queries on users' sensitive subjects. Third, we discuss the algorithm implementation for the privacy model. Finally, the effectiveness of our approach is demonstrated by theoretical analysis and experimental evaluation.

Detection of COVID-19 severity using blood gas analysis parameters and Harris hawks optimized extreme learning machine

“…Therefore, we believe that the use of the bHHOSRL_KELM model can make a more accurate clinical decision-making. Due to its great optimization capability, the proposed HHOSRL algorithm can also be applied to solve other problems, such as problems in video deblurring [ 73 ], microgrid planning [ 74 ], information retrieval services [ [75] , [76] , [77] ], image dehazing [ 78 ], kayak cycle phase segmentation [ 79 ], human motion capture [ 80 ], fault detection [ 81 ], video coding optimization [ 82 ], outlier detection [ 83 ], location-based services [ 84 , 85 ], image retrieval [ 86 ], multivariate time series analysis [ 87 ] and multi-objective problems [ 88 ].…”

Constructing dummy query sequences to protect location privacy and query privacy in location-based services

“…However, the work takes into account only the textual feature of a single user query, without considering the semantic relevance between users' current queries and users' historical queries, consequently, making it still possible for an attacker of rich prior knowledge to rule out the dummies. Then, the authors proposed a similar privacy protection approach for book search service in a digital library [32]. In summary, most of the existing methods did not fully consider the data distribution characteristics for users' queries, and also did not consider the semantic associations between query locations and query attributes (e.g., it is not appropriate to query subway stations in the countryside), as a result, leading to a negative impact on the quality of constructed dummy queries, and increasing the exposure risk of user privacy [2].…”

“…However, this kind of method generally requires the change to the existing LBS algorithm on the server, and the support of additional hardware and algorithms, thereby, decreasing its actual usability in practice. (4) In a dummy-based method, each user query is submitted together with a group of dummy queries to the server to make it difficult for the untrusted server to infer the location or attribute related to the user query [9,32]. However, the effectiveness of this kind of method depends on the quality of dummy query construction, i.e., it is easily threatened by inference attacks based on query feature distribution [2].…”

“…However, the effectiveness of this kind of method depends on the quality of dummy query construction, i.e., it is easily threatened by inference attacks based on query feature distribution [2]. In addition, the existing methods generally consider only location privacy [9] or query privacy [32], without considering both as a whole (e.g., the semantic association between the location and the attribute from the same query), as a result, decreasing the quality of dummy query construction.…”

“…In the system framework of Fig. 1, the server-side is untrusted, which is considered as the biggest potential attacker [32], so we assume that an attacker has the following ability.…”