In the digital age, while data sharing brings numerous benefits, shared data may expose privacy through data mining. Privacy-preserving data mining has become an urgent issue to address. In response, many methods for hiding association rules have emerged. In this paper, we propose an association rule hiding method based on an evolutionary algorithm, EAAIS4ARH, to eliminate or mask sensitive association rules that may reveal personal privacy or trade secrets. In EAAIS4ARH, we design an advanced initial solution generation mechanism that can significantly improve the quality of the initial solution and lay a solid foundation for the subsequent optimization process. This mechanism can also be used in other heuristic algorithm-based association rule hiding methods to improve solution quality. We introduce a unique evolutionary framework that categorizes each generation of solutions into three classes based on their performance: optimal, ordinary, and inferior. This mechanism not only promotes solution optimization, but also effectively avoids the problem of premature convergence to the local optimal solution. EAAIS4ARH also exhibits a high degree of flexibility, generating solutions that cover the spectrum from robust solutions with a zero hiding failure rate to compromise strategies that moderately sacrifice the hiding rate in exchange for a more efficient data utility, satisfying the needs of different users.Experimental results under different types of databases show that EAAIS4ARH excels in both side-effect control and data utility.

Data sharing is necessary for many practical applications. People do, however, frequently worry about the problem of privacy leaking.This study focuses on preventing the disclosure of sensitive information using association rules and frequent itemsets, which are frequently utilized in numerous applications. How to minimize side effects while hiding, particularly side effects on non-sensitive knowledge, is the difficult part of the problem. The majority of association rule hiding techniques currently in use solely consider reducing side effects on frequent itemsets (patterns), rather than rules, in order to conceal sensitive rules by reducing the statistical disclosure of the itemsets that generate such rules. In this study, we provide a concealment technique utilizing potentially risky rules to lessen adverse impacts on non-sensitive rules, not only itemsets. In addition, this method can be tailored to conceal sensitive itemsets, instead of rules. Extensive experiments show that in most cases the proposed solution can bring fewer side effects on rules, frequent patterns or data quality than existing methods.

Existing deep subspace clustering algorithms are difficult to scale to large-scale data. There are two reasons: Firstly, the existing subspace clustering algorithms almost all need to find the self-expressive coefficient matrix whose size is proportional to the square of the data set size at once. Secondly, spectral clustering needs to solve the eigenvector of the affinity matrix. These two points make the computational complexity of clustering very high when the data scale is large. This paper proposes Self-Expressive Network-Based Deep Embedded Subspace Clustering (SE-DESC), a subspace clustering method that can be applied to large-scale single-view and multi-view data. Using the idea of siamese networks, we design a self-expressive network to calculate the self-expressive coefficient between two data points, reducing the parameter amount of the self-expressive model to a constant. It can effectively avoid computational complexity. Then, we use a deeply embedded network to learn an embedding for each data point to map the data into the spectral space, avoiding the high computational complexity of spectral clustering. Extensive experiments demonstrate that SE-DESC improves the clustering performance on large-scale data compared to state-of-the-art methods.

Privacy preserving in association mining is an important research topic in the database security field. This paper has proposed a blocking-based method to solve the association rule hiding problem for data sharing. It aims at reducing undesirable side effects and increasing desirable side effects, while ensuring to conceal all sensitive rules. The candidate transactions are selected for sanitization based on their relations with border rules. Comparative experiments on real datasets demonstrate that the proposed method can achieve its goals.

When data mining techniques are applied to discover useful knowledge behind a large data collection, they are often required to preserve some confidential information, such as sensitive frequent itemsets, rules and so on. A feasible way to ensure the confidentiality is to sanitize the database and conceal sensitive information. However, the sanitization process often produces side effects, thus minimizing these side effects is an important task. An important but ignored fact is that a tradeoff exists within different side effects. When attempting to improve the performance on one dimension, the performance on other dimensions often will be degraded. In this paper, we focus on privacy preserving in association rule mining. Since there is a tradeoff within different side effects, we tried to minimize them from the view of multi-objective optimization. A rule hiding approach based on evolutionary multi-objective optimization (EMO) is proposed. It hides sensitive rules through removing identified items. The side effects on missing non-sensitive rules, ghost rules and data loss are formulated as optimization objectives. EMO is utilized to find a suitable subset of transactions for modification so that side effects can be minimized. Experimental results on real datasets illustrate that the proposed approach can achieve satisfactory results with fewer side effects. In addition, the EMO-based approach can produce multiple hiding solutions in a single run. It provides the opportunity for a user to choose freely the preferred one by preference or experience.

Today, people benefit from utilizing data mining technologies, such as association rule mining methods, to find valuable knowledge residing in a large amount of data. However, they also face the risk of exposing sensitive or confidential information, when data is shared among different organizations. Thus, a question arise: how can we prevent that sensitive knowledge is discovered, while ensuring that ordinary non-sensitive knowledge can be mined to the maximum extent possible. In this paper, we address the problem of privacy preserving in association rule mining from the perspective of multi-objective optimization. A new hiding method based evolutionary multi-objective optimization (EMO) is proposed and the side effects generated by the hiding process are formulated as optimization goals. EMO is used to find candidate transactions to modify so that side effects are minimized. Comparative experiments with exact methods on real datasets demonstrated that the proposed method can hide sensitive rules with fewer side effects.

When people utilize data mining techniques to discover useful knowledge behind large database, they also have the requirement to preserve some information so as not to be mined out, such as sensitive frequent item sets, rules, classification tree and the like. A feasible way to address this problem is to sanitize the database to conceal the sensitive information. In this paper, we focus on privacy preserving in association rule mining. In light of the tradeoff between hiding sensitive rules and disclosing non-sensitive ones during hiding process, we tackle this problem from a point view of multi-objective optimization. A novel association rule hiding approach was proposed based on evolutionary multi-objective optimization (EMO) algorithm. It adopted the model of hiding sensitive rules by deleting some items in database. Three side effects, including sensitive rules not hidden, non-sensitive lost rules and spurious rules were formulated as objectives to be minimized. The EMO algorithm was utilized to find a suitable subset of transactions to modify so that the three side effects can be minimized. Experiment results were reported to show the effectiveness of the proposed approach.