Filters








655 Hits in 2.7 sec

Publishing Sensitive Transactions for Itemset Utility

Yabo Xu, Benjamin C. M. Fung, Ke Wang, Ada W. C. Fu, Jian Pei
2008 2008 Eighth IEEE International Conference on Data Mining  
We consider the problem of publishing sensitive transaction data with privacy preservation. High dimensionality of transaction data poses unique challenges on data privacy and data utility.  ...  On one hand, re-identification attacks tend to use a subset of items that infrequently occur in transactions, called moles.  ...  Data Utility Typically transaction data are published for data mining applications where sets of items that co-occur frequently, also called frequent itemsets in [7] , represent associations between items  ... 
doi:10.1109/icdm.2008.98 dblp:conf/icdm/XuFWFP08 fatcat:r2oxandc7va2vjglvkclpq4lii

Hiding Sensitive High Utility and Frequent Itemsets Based on Constrained Intersection Lattice

Huynh Trieu Vy, Le Quoc Hai, Nguyen Thanh Long, Truong Ngoc Chau, Le Quoc Hieu
2022 Cybernetics and Information Technologies  
Its goal is to remove sensitive high utility and frequent itemsets from a database before sharing it for data mining purposes while minimizing the side effects.  ...  Hiding high utility and frequent itemset is the method used to preserve sensitive knowledge from being revealed by pattern mining process.  ...  In order to select the method for hiding sensitive high utility and frequent itemset, Liu, Xu and Lv [12] have defined a maximal utility border and a minimal utility border notions for sensitive itemset  ... 
doi:10.2478/cait-2022-0001 fatcat:is3sfsqmmfan3i5b4e5z6jfnjy

On differentially private frequent itemset mining

Chen Zeng, Jeffrey F. Naughton, Jin-Yi Cai
2012 Proceedings of the VLDB Endowment  
Related work has proposed differentially private algorithms for the top-k itemset mining problem ("find the k most frequent itemsets".)  ...  We consider differentially private frequent itemset mining. We begin by exploring the theoretical difficulty of simultaneously providing good utility and good privacy in this task.  ...  To utilize the geometric mechanism, we need to compute the sensitivity of q.  ... 
doi:10.14778/2428536.2428539 pmid:24039383 pmcid:PMC3771517 fatcat:aly5rcjiybglvcm52li5pfs3he

Hiding co-occurring frequent itemsets

Osman Abul
2009 Proceedings of the 2009 EDBT/ICDT Workshops on - EDBT/ICDT '09  
Knowledge hiding, hiding rules/patterns that are inferable from published data and attributed sensitive, is extensively studied in the literature in the context of frequent itemsets and association rules  ...  What is different from the classical frequent hiding is the new sensitivity definition: an itemset set is sensitive if its itemsets appear altogether within the frequent itemset mining results.  ...  transaction list for every sensitive itemset and computing the number of sensitive transactions to be sanitized, (4) sorting the sensitive transactions by size, (5) sanitizing the transaction by removing  ... 
doi:10.1145/1698790.1698810 dblp:conf/edbtw/Abul09 fatcat:vqjoyxe73bcc7gy3mxoq4ywcwq

High utility-itemset mining and privacy-preserving utility mining

Jerry Chun-Wei Lin, Wensheng Gan, Philippe Fournier-Viger, Lu Yang, Qiankun Liu, Jaroslav Frnda, Lukas Sevcik, Miroslav Voznak
2016 Perspectives in Science  
In this paper, we focus on the issues of HUIM and privacy-preserving utility mining (PPUM), and present two evolutionary algorithms to respectively mine HUIs and hide the sensitive high-utility itemsets  ...  Extensive experiments showed that the two proposed models for the applications of HUIM and PPUM can not only generate the high quality profitable itemsets according to the user-specified minimum utility  ...  For the purpose of PPUM in this paper, the sensitive high-utility itemsets are required to be hidden through transaction deletion in the sanitization process.  ... 
doi:10.1016/j.pisc.2015.11.013 fatcat:t5y7zxkhkzc7rpdopq7gbs4lwi

Frequent Itemsets Mining With Differential Privacy Over Large-Scale Data

Xinyu Xiong, Fei Chen, Peizhi Huang, Miaomiao Tian, Xiaofang Hu, Badong Chen, Jing Qin
2018 IEEE Access  
Current solutions for this problem cannot well balance efficiency, privacy, and data utility over large-scale data.  ...  Based on the ideas of sampling and transaction truncation using length constraints, our algorithm reduces the computation intensity, reduces mining sensitivity, and thus improves data utility given a fixed  ...  For the above two utility measures, the larger F-Score is, the closer the frequent itemsets to the real itemsets; it indicates that the utility of the algorithm is higher.  ... 
doi:10.1109/access.2018.2839752 fatcat:zh7v5mexkrgvlj3it5jyxl6sry

Transactional Data Anonymization for Privacy and Information Preservation via Disassociation and Local Suppression

Xiangwen Liu, Xia Feng, Yuquan Zhu
2022 Symmetry  
Disassociation is a popular method for transactional data anonymization against re-identification attacks in privacy-preserving data publishing.  ...  datasets, thus decreasing the data quality of the published transactions.  ...  The itemsets to be anonymized and sensitive items to be protected are specified by data publishers.  ... 
doi:10.3390/sym14030472 fatcat:yfqxmaztenczbpqslowkanpoga

Privacy preserving association rule hiding using border based approach

Suma B., Shobha G.
2021 Indonesian Journal of Electrical Engineering and Computer Science  
In this paper, we introduce a border-based algorithm for hiding sensitive association rules.  ...  In the majority of the situations, data mining results contain sensitive information about individuals and publishing such data will violate individual secrecy.  ...  [10] proposed SIF-IDF technique that utilizes TF-IDF measure to determine the similarity between transactions and sensitive itemsets.  ... 
doi:10.11591/ijeecs.v23.i2.pp1137-1145 fatcat:bqzyk7wztvbv5aygwlsqohgaqu

Privacy Preserving Utility Mining: A Survey [article]

Wensheng Gan, Jerry Chun-Wei Lin, Han-Chieh Chao, Shyue-Liang Wang,, Philip S. Yu
2018 arXiv   pre-print
for PPUM.  ...  However, analysis of these data with sensitive private information raises privacy concerns.  ...  In some real-world applications, the sensitive high-utility patterns (i.e., itemsets, It has good performance on condense database, but has high overlap sensitive itemsets. 2010 FPUTT [17] Transaction  ... 
arXiv:1811.07389v1 fatcat:upooi44vzretxavpkp2lie735i

An Optimization based Modified Maximum Sensitive Item-Sets Conflict First Algorithm (MSICF) for Hiding Sensitive Item-Sets

D. JayaKumari, Nistala. V. E. S.Murthy, S. Srinivasa Suresh
2013 International Journal of Computer Applications  
The MMSICF algorithm computes the sensitive itemsets by utilizing the user defined utility threshold value.  ...  In privacy preserving utility mining, some sensitive itemsets are hidden from the database according to certain privacy policies.  ...  For example, } , { B A is a sensitive itemset ) 120 (   , having utility value 200 ) , (  B A u .  ... 
doi:10.5120/12479-8881 fatcat:hmmumjsbgrbzbmafrptno4orni

Association rule hiding using integer linear programming

Suma B., Shobha G.
2021 International Journal of Power Electronics and Drive Systems (IJPEDS)  
Hence, association rule hiding emerged as one of the powerful techniques for hiding sensitive knowledge that exists in data before it is published.  ...  The solution of the integer linear program determines the transactions that need to be sanitized in order to conceal the sensitive rules while minimizing the impact of sanitization on the non-sensitive  ...  [21] utilized ILP to formulate a CSP that determines the least number of transaction sanitizations in order to conceal sensitive itemsets.  ... 
doi:10.11591/ijece.v11i4.pp3451-3458 fatcat:onlp2lj375gsphdcgrzr32xx2m

Privacy Preserving Web Query Log Publishing: A Survey on Anonymization Techniques [article]

Amin Milani Fard
2012 arXiv   pre-print
Releasing Web query logs which contain valuable information for research or marketing, can breach the privacy of search engine users.  ...  Therefore rendering query logs to limit linking a query to an individual while preserving the data usefulness for analysis, is an important research problem.  ...  Itemset based utility [20] is another utility measure which captures frequent itemsets in transaction data.  ... 
arXiv:1211.2354v1 fatcat:5cqn62az5vfyvonn7wjmdwproy

An effective scheme for top-k frequent itemset mining under differential privacy conditions

Wenjuan Liang, Hong Chen, Jing Zhang, Dan Zhao, Cuiping Li
2020 Science China Information Sciences  
To promote the utility of the release result, a potential solution evaluated in previously published studies was to decrease the dimension of long transactions in a differentially private manner before  ...  An effective scheme for top-k frequent itemset mining under differential privacy conditions.  ...  To promote the utility of the release result, a potential solution evaluated in previously published studies was to decrease the dimension of long transactions in a differentially private manner before  ... 
doi:10.1007/s11432-018-9849-y fatcat:byhvt7vr3ff23nst2zrwbewvde

PrivBasis: Frequent Itemset Mining with Differential Privacy [article]

Ninghui Li, Wahbeh Qardaji, Dong Su, Jianneng Cao
2012 arXiv   pre-print
We introduce algorithms for privately constructing a basis set and then using it to find the most frequent itemsets.  ...  In this paper, we study the problem of how to perform frequent itemset mining on transaction databases while satisfying differential privacy.  ...  Hence the sensitivity of publishing all bin counts for one basis is 1; and the sensitivity for publishing counts for all bases is w. In Algorithm 1, lines 2 to 11 compute these noisy bin frequencies.  ... 
arXiv:1208.0093v1 fatcat:2gvi5z4bhffojex7rjazczv4gi

PrivBasis

Ninghui Li, Wahbeh Qardaji, Dong Su, Jianneng Cao
2012 Proceedings of the VLDB Endowment  
In this paper, we study the problem of how to perform frequent itemset mining on transaction databases while satisfying differential privacy.  ...  We introduce algorithms for privately constructing a basis set and then using it to find the most frequent itemsets.  ...  Hence the sensitivity of publishing all bin counts for one basis is 1; and the sensitivity for publishing counts for all bases is w. In Algorithm 1, lines 2 to 11 compute these noisy bin frequencies.  ... 
doi:10.14778/2350229.2350251 fatcat:jfhgyho54nc3vkgr2kmr3jqloa
« Previous Showing results 1 — 15 out of 655 results