International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064 Index Copernicus Value (2013): 6.14 | Impact Factor (2013): 4.438 Volume 4 Issue 6, June 2015 www.ijsr.net Licensed Under Creative Commons Attribution CC BY Supporting Privacy Protection in Personalized Web Search with Secured User Profile Archana R.Ukande 1 , Nitin Shivale 2 1 Department of Computer Science, BSITR, Wagholi, Pune, India 2 Assistant Professor Department of Computer Science, BSITR, Wagholi, Pune, India Abstract: Web search engines (e.g. Google, Yahoo, Microsoft Live Search, etc.) are widely used to find certain data among a huge amount of information in a minimal amount of time. These useful tools also pose a privacy threat to the users: web search engines profile their users by storing and analyzing past searches submitted by them. For improving better search quality the String Similarity Match Algorithm (SSM Algorithm) can be implemented with the proposed. Current solutions propose new mechanisms that introduce a high cost in terms of computation and communication, to address this privacy threat. Personalized search is a promising way to improve the accuracy of web search, also it is attracting much attention recently. Effective personalized search requires collecting and aggregating user information, which often raises serious concerns of privacy infringement for many users. These concerns have become one of the main barriers for deploying personalized search applications, and privacy-preserving personalization is a great challenge. Adversaries are tried to resist in proposed system with the help of broader background knowledge (i.e. richer relationship among topics). Richer relationship means we generalize the user profile results by using the background knowledge which is going to store in history. Through this we can hide the user search results. With the help of this mechanism, privacy can be achieved. Keywords: Privacy protection; risk; profile; personalized web search; utility 1. Introduction Novel protocol is proposed specially designed to protect the users’ privacy in front of web search profili ng. Adversaries are tried to resist in proposed system with the help of broader background knowledge i.e. knowing richer relationship among topics. Richer relationship means we generalize the user profile results by using the background knowledge which is going to store in history. Through this we can hide the user search results. In the existing System, Greedy DP and, Greedy IL algorithm it takes large computational and communication time. For generalize the retrieved data by using the background knowledge [1], [5], [3], [7] through this adversaries can be avoided. Privacy protection in publishing transaction data is an important problem. A key feature of data transaction is the extreme scarcity, which renders any single technique ineffective in anonymizing such data. Among recent works, some suffer from performance drawbacks, some incur high information loss and some result in data hard to interpret. This approach proposes to integrate generalization and compression to reduce information loss. However, the integration is non-trivial. Novel techniques are proposed to address the efficiency and scalability challenges. A few previous studies [8], [9] suggest that people are willing to compromise privacy if the personalization by supplying user profile to the search engine yields better search quality 2. Literature Review A. Privacy Protection In Personalized Search In privacy protection, analytically observe the concern of privacy preservation in personalized search [10]. Here discriminate and describe four levels of privacy protection, and analyze numerous software architectures for personalized search. It shows that client-side personalization has advantages over the existing server- side personalized search services in preserving privacy in this situation; personalized web search cannot be done at the individual user level, but is possible at the group level. This may reduce the effectiveness of personalization because a group's information need explanation is used to model an individual user's information need. However, if the group is appropriately constructed so that people with similar interests are grouped together, it has much richer user information to offset the sparse explanation of individual user information requirements. Thus the search performance may essentially be improved because of the availability of more information from the group profile [11] and [12]. In this circumstance, personalized web search cannot be done at the distinct user level, but is possible at the group level. This may reduce the effectiveness of personalization because a group's information need description is used to model an individual user's information need. However, if the group is properly constructed so that people with comparable interests are grouped together, it may have much richer user information to offset the sparse explanation of distinct user information needs. Thus the search performance may really be better because of the accessibility of more information from the group profile a. Advantages 1. The architecture has an advantage of allowing for the use of a search engine's internal resources. 2. It improves the accuracy of web search. b. Disadvantages 1. It does not fully protect user privacy. 2. They were not discussed different levels of privacy protection provided by search engines depending on a user's preference for the tradeoff between the privacy concern and the improved search service quality. Paper ID: SUB155911 2500