Differentially private 1R classification algorithm using artificial bee colony and differential evolution

Zorarpacı, Ezgi; Özel, Selma Ayşe

doi:10.1016/j.engappai.2020.103813

Cited by 14 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is a mandatory step when the exclusion criteria may not filter irrelevant studies from this review. For example, metaheuristic-based algorithms have been proposed for feature selection [16], [17] and rule classification [18], [19]. Thus, the results of this step included 59 candidate-related studies.…”

Section: ) Full Paper Scanmentioning

confidence: 99%

Preserving Privacy in Association Rule Mining Using Metaheuristic-Based Algorithms: A Systematic Literature Review

Aljehani,

Alotaibi

2024

IEEE Access

View full text Add to dashboard Cite

The current state of Association Rule Mining (ARM) technology is heading towards a critical yet profitable direction. The ARM process uncovers numerous association rules, determining correlations between itemsets, forming building blocks that have led to revolutionary scientific discoveries. However, a high level of privacy is vital for protecting sensitive rules, raising privacy concerns. Researchers recently highlighted challenges in the Privacy-Preserving Association Rule Mining (PPARM) field. Many studies have proposed workaround for the PPARM dilemma by using metaheuristics. This paper conducts a systematic literature review on metaheuristic-based algorithms addressing PPARM challenges. It explores existing studies, providing insights into diverse metaheuristic approaches tackling PPARM problems. A detailed taxonomy is presented, providing a structured classification of metaheuristic-based algorithms specific to PPARM. This classification facilitates a nuanced understanding of the field by categorizing these algorithms into metaphor-based and non-metaphor-based groups with discussion of the nature of the representation schemes for each category identified in the survey. This review extends its analysis to encompass the latest applied approaches, highlighting the diversification of existing metaheuristic algorithms in the PPARM context. Moreover, common datasets and evaluation metrics identified from selected studies are documented to provide a deeper understanding of the methodological choices made by researchers in this domain. Finally, a discussion of existing challenges and potential future directions are presented. This review serves as a helpful guide that outlines previous research and presents potential future opportunities of metaheuristic-based algorithms in the context of PPARM.

show abstract

Section: ) Full Paper Scanmentioning

confidence: 99%

Preserving Privacy in Association Rule Mining Using Metaheuristic-Based Algorithms: A Systematic Literature Review

Aljehani,

Alotaibi

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Very few works have focused on nature-inspired algorithms under the constraints of differential privacy. While PrivGene [54] has been the only work investigating differentially private genetic algorithms, other works have made use of swarm intelligence and evolutionary computation alongside differential privacy [36,55]. However, these works either did not make the nature-inspired algorithms private [55], or focus on census protocols [36] instead of DP selection.…”

Section: Related Workmentioning

confidence: 99%

Differentially Private Simple Genetic Algorithms

Humphries

Kerschbaum

2023

PoPETs

View full text Add to dashboard Cite

The differentially private (DP) selection problem is a fundamental building block in the private literature that is commonly solved with the exponential mechanism. It is well known that efficiency is the major drawback of the exponential mechanism, as the utility function must be computed for all elements in the domain. Genetic algorithms (GAs) use the principles of evolution in nature to efficiently search through large domains and select the best candidate. We observe that GAs have many appealing properties for DP Selection. These include being robust to noisy objectives, placing no restriction on the utility function, and efficient runtime for large domains. However, prior work investigating DP GAs has shown poor utility in practice and often gives the highest utility when zero generations are conducted (indicating that GA operations are not beneficial under DP). This work provides a new DPGA based on the simple GA that addresses the weaknesses of prior solutions. We reduce the destructive nature of previous GA operators and utilize several techniques to reduce the noise from DP. Our modifications allow us to utilize the GA operators over multiple generations (under DP) and improve the GA's overall utility over zero generation techniques. Our work shows that private GAs are competitive with state-of-the-art general and problem-specific solutions to the DP selection problem, with runtime sublinear in the domain size.

show abstract

“…An implementation of Holte's One Rule classification algorithm with output perturbation technique has been performed by Zorarpacı and Özel (2020) who have also taken the advantage of artificial bee colony and differential evolution optimization algorithms to improve performance of the differentially private One Rule implementation named as DP1R. In this study, the performance of DP1R is compared with the differentially private versions of the SVM, logistic regression, random tree, and ID3 algorithms (Zorarpacı & Özel, 2020).…”

Section: Differentially Private Classificationmentioning

confidence: 99%

“…According to the literature, the majority of the existing differentially private classification algorithms use output perturbation technique to provide privacy of the sensitive data (Blum et al, 2005;Bojarski et al, 2014;Chaudhuri & Monteleoni, 2008;Fletcher & Islam, 2015, 2019Friedman & Schuster, 2010;Gursoy et al, 2017;Jagannathan et al, 2009Jagannathan et al, , 2013Patil & Singh, 2014;Rana et al, 2015;Rubinstein et al, 2009;Vaidya et al, 2013;Zorarpacı & Özel, 2020). However, Mivule et al (2012) have proposed perturbing the input data to find an optimal noise amount, which provides differential privacy guarantee for achieving satisfactory classification results.…”

Section: Differentially Private Classificationmentioning

confidence: 99%

“…In the literature, differentially private classification algorithms based on k-NN, ID3, random decision trees, and forests, Naïve Bayes, SVM, and Holte's One Rule have been proposed (Bojarski et al, 2014;Fletcher & Islam, 2015, 2019Friedman & Schuster, 2010;Gursoy et al, 2017;Rubinstein et al, 2009;Senekane, 2019;Vaidya, Shafiq, Basu, & Hong, 2013;Zhang, Hao, & Wang, 2019;Zorarpacı & Özel, 2020). Briefly overviewing the literature concerning classification with differential privacy, it can be seen that, the majority of the existing methods employ output perturbation technique from differential privacy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Privacy preserving classification over differentially private data

Zorarpacı

Özel

2020

WIREs Data Min & Knowl

Self Cite

View full text Add to dashboard Cite

Privacy preserving data classification is an important research area in data mining field. The goal of a privacy preserving classification algorithm is to protect the sensitive information as much as possible, while providing satisfactory classification accuracy. Differential privacy is a strong privacy guarantee that enables privacy of sensitive data stored in a database by determining the ratio of sensitive information leakage with respect to an ɛ parameter. In this study, our aim is to investigate the classification performance of the state‐of‐the‐art classification algorithms such as C4.5, Naïve Bayes, One Rule, Bayesian Networks, PART, Ripper, K*, IBk, and Random tree for performing privacy preserving classification. To preserve privacy of the data to be classified, we applied input perturbation technique coming from differential privacy, and observed the relationship between the ɛ parameter values and accuracy of the classifiers. To our best knowledge, this article is the first study that analyzes the performances of the well‐known classification algorithms over differentially private data, and discovers which datasets are more suitable for privacy preserving classification when input perturbation is applied to provide data privacy. The classification algorithms are compared by using the differentially private versions of the well‐known datasets from the UCI repository. According to the experimental results, we observed that, as ɛ parameter value increases, better classification accuracies are achieved with lower privacy levels. When the classifiers are compared, Naïve Bayes classifier is the most successful method. The ɛ parameter should be greater than or equal to 2 (i.e., ɛ ≥2) to achieve cloud server is malicious and untrusted, sensitive data will satisfactory classification accuracies. This article is categorized under: Commercial, Legal, and Ethical Issues > Security and Privacy Technologies > Classification

show abstract

Differentially private 1R classification algorithm using artificial bee colony and differential evolution

Cited by 14 publications

References 22 publications

Preserving Privacy in Association Rule Mining Using Metaheuristic-Based Algorithms: A Systematic Literature Review

Preserving Privacy in Association Rule Mining Using Metaheuristic-Based Algorithms: A Systematic Literature Review

Differentially Private Simple Genetic Algorithms

Privacy preserving classification over differentially private data

Contact Info

Product

Resources

About