Publishing Set-Valued Data Against Realistic Adversaries

Liu, Junqiang

doi:10.1007/s11390-012-1203-6

Cited by 12 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Suppose g 1 , g 2 , .., g m are categories of items in t k and their item frequency in t k are f 1 , f 2 , ..., f m , respectively. From the Equations (4) and (5), the condition that t k in a database does not satisfy the inequality WR t k ,g j > MTV t k becomes for all j ∈ {1, ..., m}. Under this condition the Algorithms 1 and 2 cannot output respective I t k and a pair of P for the t k .…”

Section: Applicability Of the Proposed Methodsmentioning

confidence: 99%

“…For example, Bob likes to access autocars.net which is categorized as an automobile website, but replacing the website name with its category i.e., automobile, it does not hide that Bob has a tendency toward automobiles. In addition, employing generalization technique such as full domain generalization in set-valued database leads significant reduction in data utility [4] and causes item loss in databases if several items from the same category appear together in one record [5]. As a result, data recipients cannot obtain maximum utility from the database.Suppression based data anonymization techniques [4,6,7] can be more realistic for hiding personal tendency since certain items in a record are removed so that there is no clue to find the suppressed items.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Data Anonymization for Hiding Personal Tendency in Set-Valued Database Publication

Gunawan

Mambo

2019

Future Internet

View full text Add to dashboard Cite

Set-valued database publication has been increasing its importance recently due to its benefit for various applications such as marketing analysis and advertising. However, publishing a raw set-valued database may cause individual privacy breach such as the leakage of sensitive information like personal tendencies when data recipients perform data analysis. Even though imposing data anonymization methods such as suppression-based methods and random data swapping methods to such a database can successfully hide personal tendency, it induces item loss from records and causes significant distortion in record structure that degrades database utility. To avoid the problems, we proposed a method based on swapping technique where an individual's items in a record are swapped to items of the other record. Our swapping technique is distinct from existing one called random data swapping which yields much structure distortion. Even though the technique results in inaccuracy at a record level, it can preserve every single item in a database from loss. Thus, data recipients may obtain all the item information in an anonymized database. In addition, by carefully selecting a pair of records for item swapping, we can avoid excessive record structure distortion that leads to alter database content immensely. More importantly, such a strategy allows one to successfully hide personal tendency without sacrificing a lot of database utility.Future Internet 2019, 11, 138 2 of 16 of hiding personal tendency we give the following example. An internet user, Bob, accessed various websites where most of the websites that he visited can be categorized as automobile websites, and to this end we can say that Bob has a strong tendency to the automobile category. The web address that Bob accessed are collected by On-line advertisement company, says AdOn. In one day AdOn release the log of the internet users, including Bob's web access log to its collaborator company, namely AdOff. Unfortunately, an irresponsible agent who is working in AdOff knows the information about Bob's tendency by analyzing his browsing history and starts to send email spam that contains interesting information about automobiles, as well as inserting a malicious link in the email, due to his curiosity Bob may get in trouble if he clicks the malicious link.The illustration story tells us that the spammer sends email spam that is precisely related to the targeted personal tendency. However, if Bob's tendency is hidden, the spammer might fail to trap Bob, since the email spam would not be too precise to Bob's personal tendency. As a result, even if Bob receives the email he might ignore it and refrain to click a link that does not attract him.As the nature of a set-valued database where an individual is directly correlated to his/her items, accordingly, prior to publishing such a database to the public, one should consider a data anonymization process such that the personal tendency of individuals can be protected in a published database. Several data anonymization techniques...

show abstract

Section: Applicability Of the Proposed Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

Data Anonymization for Hiding Personal Tendency in Set-Valued Database Publication

Gunawan

Mambo

2019

Future Internet

View full text Add to dashboard Cite

show abstract

“…It is further assumed in [30] that adversary has unbounded background knowledge and knows both sensitive and non-sensitive items in database. There is a critique [14] that this further assumption is unrealistic since set-valued data has arbitrary items in its records. k m -anonymity [22] assumed that adversary has knowledge about up to m items from a specific record in the database.…”

Section: Adversary Knowledgementioning

confidence: 99%

“…Records or tuples in set-valued database may contain different number of items and if we consider each item as a quasiidentifier like in relational database, then it will have very high dimensionality [14]. As a result, applying k-anonymity will not be effective due to the curse of high dimensionality in set-valued database [1].…”

Section: Introductionmentioning

confidence: 99%

Set-valued Data Anonymization Maintaining Data Utility and Data Property

Gunawan

Mambo

2018

Proceedings of the 12th International Conference on Ubiquitous Information Management and Communication

View full text Add to dashboard Cite

Set-valued database publication has been attracting much attention due to its benefit for various applications like recommendation systems and marketing analysis. However, publishing original database directly is risky since an unauthorized party may violate individual privacy by associating and analyzing relations between individuals and set of items in the published database, which is known as identity linkage attack. Generally, an attack is performed based on attacker's background knowledge obtained by a prior investigation and such adversary knowledge should be taken into account in the data anonymization. Various data anonymization schemes have been proposed to prevent the identity linkage attack. However, in existing data anonymization schemes, either data utility or data property is reduced a lot after excessive database modification and consequently data recipients become to distrust the released database. In this paper, we propose a new data anonymization scheme, called sibling suppression, which causes minimum data utility lost and maintains data properties like database size and the number of records. The scheme uses multiple sets of adversary knowledge and items in a category of adversary knowledge are replaced by other items in the category. Several experiments with real dataset show that our method can preserve data utility with minimum lost and maintain data property as the same as original database. CCS CONCEPTS • Security and privacy → Data anonymization and sanitization; Database and storage security;

show abstract

A Sensitivity-Adaptive $$\rho $$-Uncertainty Model for Set-Valued Data

Chen

Wang

et al. 2017

Financial Cryptography and Data Security

View full text Add to dashboard Cite

Publishing Set-Valued Data Against Realistic Adversaries

Cited by 12 publications

References 22 publications

Data Anonymization for Hiding Personal Tendency in Set-Valued Database Publication

Data Anonymization for Hiding Personal Tendency in Set-Valued Database Publication

Set-valued Data Anonymization Maintaining Data Utility and Data Property

A Sensitivity-Adaptive $$\rho $$-Uncertainty Model for Set-Valued Data

Contact Info

Product

Resources

About