Efficient perturbation techniques for preserving privacy of multivariate sensitive data

An efficient perturbation approach for multivariate data in sensitive and reliable data mining

Data perturbation under differential privacy constraint is an important approach of protecting data privacy. However, as the data dimensions increase, the privacy budget allocated to each dimension decreases and thus the amount of noise added increases, which eventually leads to lower data utility in training tasks. To protect the privacy of training data while enhancing data utility, we propose a Utility-aware training data Privacy Perturbation scheme based on attribute Partition and budget Allocation (UPPPA). UPPPA includes three procedures: the quantification of attribute privacy and attribute importance, attribute partition, and budget allocation. The quantification of attribute privacy and attribute importance based on information entropy and attribute correlation provide an arithmetic basis for attribute partition and budget allocation. During the attribute partition, all attributes of training data are classified into high and low classes to achieve privacy amplification and utility enhancement. During the budget allocation, a γ-privacy model is proposed to balance data privacy and data utility so as to provide privacy constraint and guide budget allocation. Three comprehensive sets of real-world data are applied to evaluate the performance of UPPPA. Experiments and privacy analysis show that our scheme can achieve the tradeoff between privacy and utility.

In this paper we present PasS (Privacy as a Service); a set of security protocols for ensuring the privacy and legal compliance of customer data in cloud computing architectures. PasS allows for the secure storage and processing of users’ confidential data by leveraging the tamper-proof capabilities of cryptographic coprocessors. Using tamper-proof facilities provides a secure execution domain in the computing cloud that is physically and logically protected from unauthorized access. PasS central design goal is to maximize users’ control in managing the various aspects related to the privacy of sensitive data. This is achieved by implementing user-configurable software protection and data privacy mechanisms. Moreover, PasS provides a privacy feedback process which informs users of the different privacy operations applied on their data and makes them aware of any potential risks that may jeopardize the confidentiality of their sensitive information. To the best of our knowledge, PasS is the first practical cloud computing privacy solution that utilizes previous research on cryptographic coprocessors to solve the problem of securely processing sensitive data in cloud computing infrastructures.

The dramatic growth in machine learning has brought in significant features and quantified non‐linear associations in the data derived from sensitive medical datasets. The data should be preserved without influencing the associated classifications by applying a robust, effective and reliable data perturbation technique before enforcing ensemble classification. In this paper, an Integrated Condensation Scheme imposed Privacy Preserving Rotation‐based Data Perturbation and Ensemble Classification (ICS‐PPR‐DPEC) is proposed for ensuring privacy of such sensitive data. Condensation Algorithm‐based Data Perturbation is used for constructing homogenous groups determined from the distance between tuples. It also generates a rotation matrix for conducting perturbation that ensures higher data sensitivity protection before it is sent for classification. Advanced Extreme Learning Machine‐based Ensemble Classification Scheme includes kernel, norm‐optimized and regularized Extreme Learning Machine (ELM)‐based classifiers for attaining predominant classification accuracy in identifying human DNA sequences. This approach facilitates classification by constructing ensembles which are trained through randomly resampled ELM classifiers. It includes an objective function that systematically improves the accuracy and diversity among resulting ensembles. The experimental results of the proposed ICS‐PPR‐DPEC are found to be excellent in terms of classification Accuracy, Precision, Recall, and Kappa statistic when compared to the benchmarked techniques.

Cloud computing paradigm enables the users toaccess the outsourced data from the cloud server without the hardware and software management. For the effective utilization of sensitive data from CSP, the data owner encrypts before outsourcing to the cloud server. To protect data in cloud, data privacy is the challenging task. In order to address this problem, we proposed an efficient data security method using cryptographic techniques. Thus, the proposed method not only encrypts the sensitive data, but also detects the dishonest party to access the data using combined hash functions. We have analyzed the proposed method in terms of storage, communication and computational overheads. The result shows that the proposed security method is more efficient than the existing security system.

Generative Adversarial Networks (GANs) have demonstrated their remarkable capacity to learn the training data distribution and produce high-quality synthetic images, which have been widely adopted in image recognition tasks in remote sensing research communities. However, previous work has shown that using GANs does not preserves privacy, e.g., being susceptible to membership attacks, while sensitive information is vulnerable to nefarious activities. This drawback is considered severe in remote sensing communities, in which critical researches highly value the security and privacy of the image content. Thus, to publicly share sensitive data for supporting critical researches, in the meantime guarantee the model accuracy trained from privacy-preserving data, this work develops GANs within the Differential Privacy (DP) framework, and proposes a Remote Sensing Differentially Private Generative Adversarial Networks (RS-DPGANs) for both privacy-preserving synthetic image generation and classification. Our RS-DPGANs is capable of releasing safe-version of synthetic data meanwhile obtaining favorable classification r esults, w hich gives rigorous guarantees for the privacy of sensitive data and balance between the model accuracy and privacy-preserving degree. Extensive empirical and statistical results both confirm the effectiveness of our framework.

In the age of the Internet of Things (IoT), an immense volume of data is rapidly generated and entrusted to external units, including cloud centers for storage and analysis. This implies that the data produced by IoT devices is conveyed and stored in a distant location, where it can undergo processing, examination, and utilization to extract valuable insights and facilitate informed decision-making. Privacy protection methods can be applied in IoT settings to safeguard sensitive and private information from potential security risks. Within the scope of IoT privacy, data sanitization involves the permanent and irreversible concealment of all sensitive data from extensive streams of information. Conversely, data restoration is the reverse process of data sanitization. Considering privacy preservation in IoT for data streaming, this research paper implements a Deep Learning (DL) tuned key-based data sanitization and restoration approach. The entire process of the implemented approach is handled by two significant steps such as data sanitization and data restoration. In the data sanitization step, three processes take place such as retrieval of features, key generation via Self-Adaptive Osprey Optimization (SAOO) and key tuning via Enhanced Convolutional Neural Network (ECNN). Initially, features such as raw features, statistical features and improved entropy-based features are retrieved (considering this as sensitive information. To sanitize this, key generation is the subsequent phase, where optimal keys are generated by SAOO and its security and confidentiality are ensured by the Khatri–Rao product. Then, these optimal keys are tuned by ECNN to ensure the efficacy of privacy preservation in IoT without compromising the performance of the model. Finally, the data restoration process is to recover the previously sanitized data in an IoT environment and reconstitute the original data from their sanitized form while maintaining the security and confidentiality of raw sensitive data. With these steps, the privacy of an IoT environment is protected from any form of issues. Additionally, this approach is experimentally explored to determine its efficacy using various analyses.

K-Anonymization approach for privacy preservation using data perturbation techniques in data mining

Efficient privacy preservation of big data for accurate data mining

The extensive prevalence of computing technologies in our daily lives and physical landscapes has led to the generation of vast datasets for analysis. Although, there is a growing uncertaintyregarding potential privacy breaches, as sensitive data could be exposed if not adequately protected during analysis. Many existing privacy-preserving methods encounter challenges such as inefficiency, scalability limitations, and the delicate balance between data utility and privacy conservation.
 In this study, we introduce an algorithm known as PABIDOT. PABIDOT employs optimal geometric transformations to safeguard privacy within the realm of big data. We assess the efficacy of PABIDOT through a series of experiments involving nine distinct datasets and five classification algorithms. Our results highlight PABIDOT's exceptional execution speed, scalability, resilience against potential attacks,andits accuracy in large-scale datasets.In addition, we delve into the practical implications of PABIDOT in real-world scenarios, emphasizing its adaptability across diverse industries and applications. The algorithm's robustness in safeguarding sensitive information while maintaining data integrity sets a new standard in privacy preservation. Moreover, the study sheds light on potential avenues for further advancements in the field of secure data analytics, paving the way for more comprehensive and effective privacy solutions in the era of burgeoning data generation and utilization.

As Cloud Computing becomes prevalent, more and more sensitive information are being centralized into the cloud. For the protection of data privacy, sensitive data usually have to be encrypted before outsourcing, which makes effective data utilization a very challenging task. Although traditional searchable encryption schemes allow a user to securely search over encrypted data through keywords and selectively retrieve files of interest, these techniques support only exact keyword search. This significant drawback makes existing techniques unsuitable in cloud computing as it is greatly affect system usability, rendering user searching experiences very frustrating and system efficiency very low. In this paper, for the first time we formalize and solve the problem of effective fuzzy keyword search over encrypted cloud while maintaining keyword privacy. In our solution, we exploit edit distance to quantify keyword similarity and develop new advanced technique on constructing fuzzy keyword sets which greatly reduces the storage and representation overheads. In this way, we show that our proposed solution is secure and privacy preserving, while realizing the goal of fuzzy keyword search.

BackgroundSecuring adequate data privacy is critical for the productive utilization of data. De-identification, involving masking or replacing specific values in a dataset, could damage the dataset’s utility. However, finding a reasonable balance between data privacy and utility is not straightforward. Nonetheless, few studies investigated how data de-identification efforts affect data analysis results. This study aimed to demonstrate the effect of different de-identification methods on a dataset’s utility with a clinical analytic use case and assess the feasibility of finding a workable tradeoff between data privacy and utility.MethodsPredictive modeling of emergency department length of stay was used as a data analysis use case. A logistic regression model was developed with 1155 patient cases extracted from a clinical data warehouse of an academic medical center located in Seoul, South Korea. Nineteen de-identified datasets were generated based on various de-identification configurations using ARX, an open-source software for anonymizing sensitive personal data. The variable distributions and prediction results were compared between the de-identified datasets and the original dataset. We examined the association between data privacy and utility to determine whether it is feasible to identify a viable tradeoff between the two.ResultsAll 19 de-identification scenarios significantly decreased re-identification risk. Nevertheless, the de-identification processes resulted in record suppression and complete masking of variables used as predictors, thereby compromising dataset utility. A significant correlation was observed only between the re-identification reduction rates and the ARX utility scores.ConclusionsAs the importance of health data analysis increases, so does the need for effective privacy protection methods. While existing guidelines provide a basis for de-identifying datasets, achieving a balance between high privacy and utility is a complex task that requires understanding the data’s intended use and involving input from data users. This approach could help find a suitable compromise between data privacy and utility.

In today’s digital era, the issue of data privacy remains one of the most burning concerns for companies, especially in such fields as analytics and finance which deal with the collection and processing of big amounts of clients’ sensitive information. The present study seeks to explore approaches that can be used to improve data privacy, with a clear emphasis of Differential Privacy, anonymization, and Federated learning. They seek to give individual privacy in the handling and use of their data while enabling organizations to gain insights on the data. The research focuses on the influence of the laws, such as GDPR and CCPA, in defining and enforcing privacy requirements to progressively impact the organization’s operations. In respect of this, the study, which employs qualitative analysis and case studies from the finance and analytics industry, assesses the applicability of these approaches in minimizing risks of data breaches as well as enhancing consumer trust. Thus, the research indicates that the addition of PETs to regulation acts as a viable method for increasing privacy protection, while still having the issue of cost for the implementation of new technology in terms of money and organizational change. Also, the study reveals that there is always a gap that requires individuals to adjust practice, new privacy threats, and other changes in the regulations. In conclusion of this research, the need to adopt advanced technology as a tool for business development should be married with approaches that safeguard privacy. This paper establishes that optimization of protective measures is required to advance data protection in business scenarios especially regarding sensitive financial and analytical information, recommending integration of advanced technologies with a concrete legal backing.

Vietnam: Data Privacy in a Communist ASEAN State

Data reusability has become a distinct characteristic of scientific, commercial, and administrative practices nowadays. However, an unlimited and careless reuse of data may lead to privacy breaches and unfair impacts on individuals and vulnerable groups. Data content adaption is a key aspect of preserving data privacy and fairness. Often, such content adaption affects data utility adversely. Further, the interaction between privacy protection and fairness protection can be subject to making trade-offs because mitigating privacy risks may adversely affect detecting unfairness and vice versa. Therefore, there is a need for research on understanding the interactions between data utility, privacy and fairness. To this end, in this contribution, we use concepts from causal reasoning and argue for adopting an integrated view on data content adaption for data driven decision support systems. This asks for considering the operation context wholistically. By means of two cases, we illustrate that, in some situations, local data content adaption may lead to low data quality and utility. An integrated wholistic approach, however, may result in reuse of the original data (i.e., without content adaption, thus in higher data utilization) without adversely affecting privacy and fairness. We discuss some implications of this approach and sketch a few directions for future research.