Privacy-preserving Model Research Articles

A privacy-preserving model based on differential approach for sensitive data in cloud environment

A large amount of data and applications need to be shared with various parties and stakeholders in the cloud environment for storage, computation, and data utilization. Since a third party operates the cloud platform, owners cannot fully trust this environment. However, it has become a challenge to ensure privacy preservation when sharing data effectively among different parties. This paper proposes a novel model that partitions data into sensitive and non-sensitive parts, injects the noise into sensitive data, and performs classification tasks using k-anonymization, differential privacy, and machine learning approaches. It allows multiple owners to share their data in the cloud environment for various purposes. The model specifies communication protocol among involved multiple untrusted parties to process owners data. The proposed model preserves actual data by providing a robust mechanism. The experiments are performed over Heart Disease, Arrhythmia, Hepatitis, Indian-liver-patient, and Framingham datasets for Support Vector Machine, K-Nearest Neighbor, Random Forest, Naive Bayes, and Artificial Neural Network classifiers to compute the efficiency in terms of accuracy, precision, recall, and F1-score of the proposed model. The achieved results provide high accuracy, precision, recall, and F1-score up to 93.75%, 94.11%, 100%, and 87.99% and improvement up to 16%, 29%, 12%, and 11%, respectively, compared to previous works.

Preserving Privacy of High-Dimensional Data by l-Diverse Constrained Slicing

In the modern world of digitalization, data growth, aggregation and sharing have escalated drastically. Users share huge amounts of data due to the widespread adoption of Internet-of-things (IoT) and cloud-based smart devices. Such data could have confidential attributes about various individuals. Therefore, privacy preservation has become an important concern. Many privacy-preserving data publication models have been proposed to ensure data sharing without privacy disclosures. However, publishing high-dimensional data with sufficient privacy is still a challenging task and very little focus has been given to propound optimal privacy solutions for high-dimensional data. In this paper, we propose a novel privacy-preserving model to anonymize high-dimensional data (prone to various privacy attacks including probabilistic, skewness, and gender-specific). Our proposed model is a combination of l-diversity along with constrained slicing and vertical division. The proposed model can protect the above-stated attacks with minimal information loss. The extensive experiments on real-world datasets advocate the outperformance of our proposed model among its counterparts.

Privacy-preserving mimic models for clinical named entity recognition in French

A vast amount of crucial information about patients resides solely in unstructured clinical narrative notes. There has been a growing interest in clinical Named Entity Recognition (NER) task using deep learning models. Such approaches require sufficient annotated data. However, there is little publicly available annotated corpora in the medical field due to the sensitive nature of the clinical text. In this paper, we tackle this problem by building privacy-preserving shareable models for French clinical Named Entity Recognition using the mimic learning approach to enable the knowledge transfer through a teacher model trained on a private corpus to a student model. This student model could be publicly shared without any access to the original sensitive data. We evaluated three privacy-preserving models using three medical corpora and compared the performance of our models to those of baseline models such as dictionary-based models. An overall macro F-measure of 70.6% could be achieved by a student model trained using silver annotations produced by the teacher model, compared to 85.7% for the original private teacher model. Our results revealed that these privacy-preserving mimic learning models offer a good compromise between performance and data privacy preservation.

A Lightweight Hybrid Deep Learning Privacy Preserving Model for FC-Based Industrial Internet of Medical Things.

The Industrial Internet of Things (IIoT) is gaining importance as most technologies and applications are integrated with the IIoT. Moreover, it consists of several tiny sensors to sense the environment and gather the information. These devices continuously monitor, collect, exchange, analyze, and transfer the captured data to nearby devices or servers using an open channel, i.e., internet. However, such centralized system based on IIoT provides more vulnerabilities to security and privacy in IIoT networks. In order to resolve these issues, we present a blockchain-based deep-learning framework that provides two levels of security and privacy. First a blockchain scheme is designed where each participating entities are registered, verified, and thereafter validated using smart contract based enhanced Proof of Work, to achieve the target of security and privacy. Second, a deep-learning scheme with a Variational AutoEncoder (VAE) technique for privacy and Bidirectional Long Short-Term Memory (BiLSTM) for intrusion detection is designed. The experimental results are based on the IoT-Botnet and ToN-IoT datasets that are publicly available. The proposed simulations results are compared with the benchmark models and it is validated that the proposed framework outperforms the existing system.

S-CPM: Semantic-Similarity Cluster based Privacy Preservation Model with Cell Generalization Principle

Timely data analysis on a wide variety and a large volume of data unveil valuable information or new insights. The analysis results could be used to innovate new avenues in health care service, business and e-service, etc. However, releasing, storing and reusing sensitive data to third parties results in breaching the data privacy of the individual. To combat privacy breach invasion, privacy-preserving techniques such as suppression, generalization and encryption-based privacy models have been proposed in the literature. The widely used privacy preservation model k-anonymity model prevents record-linkage invasions but fails to satisfy monotonicity property. It has more data distortion and fails to defend semantic-similarity, closeness, nearest-neighborhood data privacy breaches. Moreover, existing approaches are not scalable for the large-scale data set. The paper proposes a semantic similarity two-phase cluster based privacy preservation model. The proposed model considers both numerical and categorical attribute values for data anonymization. Two-phase clustering contains two phases. In the first phase, the t-centroid clustering algorithm is designed and used to partition a set of transaction records of data set D into a set of t-centroids based on the Euclidean distance between transaction records. In the second phase, the neighborhood-aware hierarchical clustering algorithm is designed. It is used to split a set of transaction records within clusters based on neighborhood aware attribute values. Two-phase clustering operations are carried out in parallel and scalable for Big Data sets. The proposed privacy model relies on cell generalization to combat records linkage and semantic-similarity, closeness, nearest-neighborhood privacy breach invasion. All experiments are carried out on two different datasets: Income-Census (KDD) and Bank Credit Card dataset. The experimental results demonstrate that the proposed privacy model can combat privacy breach invasion with cell generalization principles. The proposed privacy model is scalable and time efficient for large-scale data sets.

Differential and Access Policy Based Privacy-Preserving Model in Cloud Environment

Cloud computing has multiple benefits in terms of minimum cost, maximum efficiency, and high scalability, which prompts shifting a large amount of data from the local machine to the cloud environment for storage, computation, and data sharing among various parties stakeholders. However, owners do not fully trust the cloud platform operated by a third party. Therefore, security and privacy emerge as critical issues while sharing data among different parties. In this paper, a novel privacy-preserving model is proposed by utilizing encryption, differential privacy, and machine learning approaches. It facilitates data owners to share their data securely in the cloud environment. The model defines access policy and communication protocol among the involved untrusted parties for data processing and privacy preservation. The proposed model is evaluated by executing experiments using distinct datasets. The achieved results reveal that the proposed model provides high accuracy, precision, recall, and f1-score up to 98%, 98%, 97%, and 97%, respectively, over the state of the art methods.

Privacy preserving collaborative learning of generalized linear mixed model

Generalized Linear Mixed Model is one of the most pervasive class of statistical models. It is widely used in the medical domain. Training such models in a collaborative setting often entails privacy risks. Standard privacy preserving mechanisms such as differential privacy can be used to mitigate the privacy risk during training the model. However, experimental evidence suggests that adding differential privacy to the training of the model can cause significant utility loss which makes the model impractical for real world usage. Therefore, it becomes clear that the specific class of generalized linear mixed models which lose their usability under differential privacy requires a different approach for privacy preserving model training.In this work, we propose a value-blind training method in a collaborative setting for generalized linear mixed models. In our proposed training method, the central server optimizes model parameters for a generalized linear mixed model without ever getting access to the raw training data or intermediate computation values. Intermediate computation values that are shared by the collaborating parties with the central server are encrypted using homomorphic encryption. Experimentation on multiple datasets suggests that the model trained by our proposed method achieves very low error rate while preserving privacy. To the best of our knowledge, this is the first work that performs a systematic privacy analysis of generalized linear mixed model training in collaborative setting.

Hybrid optimization‐based privacy preservation of database publishing in cloud environment

AbstractThis work intends to introduce an optimization‐based privacy preservation model via selecting the optimal key matrix. Here, privacy preservation is carried out under two processes, namely, “data sanitization and restoration.” In fact, data sanitization is the data preservation method, where the data (message) are preserved using the optimal key. Similarly, data restoration is the inverse procedure of sanitization. Here, the key matrix is optimally chosen using a novel hybrid algorithm. For optimization purpose, this work deploys a hybrid optimization approach known as random‐based grey dragon algorithm (R‐GDA) that involves the concepts of both “dragonfly algorithm (DA) and grey wolf optimization (GWO) algorithm.” The novelty of the work is introduced in hybrid optimization approach R‐GDA. Eventually, the supremacy of the adopted method is validated over other existing approaches in terms of various measures such as privacy, utility, and so on. The privacy preservation in the cloud is achievable in the field of education, banking sector, military, and the research community.

Hybrid heuristic-based key generation protocol for intelligent privacy preservation in cloud sector

Cloud Computing is defined as a set of software and hardware that are used together for delivering different kinds of cloud services based on user's demand. Cloud computing secures a major role in the Information Technology (IT) industry for accessing the services at any place around the world. On the other hand, there are increasing vulnerabilities and threats in the cloud environment due to the rise in popularity and demands in cloud computing services. Data privacy and integrity are the major issues in cloud computing while storing data in various geographical locations. So, it is necessary to consider the data privacy and integrity factors in a cloud computing environment. It is difficult to construct a common platform to interact in the cloud environment. So, it is essential for implementing the security solutions, which need to provide confidentiality while exchanging the data. The main intention of this paper is to design and develop a novel artificial intelligence approach for handling the privacy preservation problem in the cloud sector. Through the process of data sanitization, the sensitive data is hidden, so that it cannot be accessed by unauthorized users. To perform the sanitization process, the heuristic-based key generations play a vital role, and here, it is solved by considering a multi-objective function with constraints like the “degree of modification, hiding ratio, and information preservation ratio”. This multi-objective problem is solved by the adoption of novel Probability Switch searched Butterfly-Moth Flame Optimization (PS-BMFO). Finally, the restoration is also performed by the same PS-BMFO-based key generation. The analysis results confirm that the suggested model preserves privacy and ensures the integrity of the user's data against unauthorized parties. From the experimental analysis, the proposed PS-BMFO gives 12.5%, 10%, 30.7%, and 12.5% enriched than GWO, JA, MFO, and BOA, respectively. Therefore, the statistical analysis shows that the developed data privacy preservation model with suggested PS-BMFO performs better than the other conventional algorithms.

Privacy-Preserving Mechanisms for Multi-Label Image Recognition

Multi-label image recognition has been an indispensable fundamental component for many real computer vision applications. However, a severe threat of privacy leakage in multi-label image recognition has been overlooked by existing studies. To fill this gap, two privacy-preserving models, Privacy-Preserving Multi-label Graph Convolutional Networks (P2-ML-GCN) and Robust P2-ML-GCN (RP2-ML-GCN), are developed in this article, where differential privacy mechanism is implemented on the model’s outputs so as to defend black-box attack and avoid large aggregated noise simultaneously. In particular, a regularization term is exploited in the loss function of RP2-ML-GCN to increase the model prediction accuracy and robustness. After that, a proper differential privacy mechanism is designed with the intention of decreasing the bias of loss function in P2-ML-GCN and increasing prediction accuracy. Besides, we analyze that a bounded global sensitivity can mitigate excessive noise’s side effect and obtain a performance improvement for multi-label image recognition in our models. Theoretical proof shows that our two models can guarantee differential privacy for model’s outputs, weights and input features while preserving model robustness. Finally, comprehensive experiments are conducted to validate the advantages of our proposed models, including the implementation of differential privacy on model’s outputs, the incorporation of regularization term into loss function, and the adoption of bounded global sensitivity for multi-label image recognition.

Securing Privacy Using Optimization and Statistical Models in Cognitive Radio Networks

Cognitive Radio Networks (CRN) are the possible and ideal solution for meeting the spectrum needs of next-generation communication systems. CRN is a promising alternative approach that allows spectrum sharing in many applications. The licensed users considered Primary Users (PU) and unlicensed users as Secondary Users (SU). Time and power consumption on security issues are considered degrading factors in performance for improving the Quality of Service (QoS). Irrespective of using different optimization techniques, the same methodology is to be updated for the task. So that, learning and optimization go hand in hand. It ensures the security in CRN, risk factors in spectrum sharing to SU for secure communication. The objective of the proposed work is to preserve the location of the SU from attackers and attain the clustering of SU to utilize the resource. Ant Colony Optimization (ACO) is implemented to increase the overall efficiency and utilization of the CRN. ACO is used to form clusters of SUs in the co-operative spectrum sensing technique. This paper deals with threat detection and classifying threats using parameters such as unlikability, context privacy, anonymity, conditional traceability, and trade-off. In this privacy-preserving model, overall accuracy is 97.4%, and it is 9% higher than the conventional models without Privacy-Preserving Architecture (PPA).

Optimization Models in Cyber-Physical Power Systems: A Review

The growing interconnection between information networks and power grids enables a more efficient and economical operation, but also introduces significant challenges in modern cyber-physical power systems, such as malicious cyber-attacks. Several cyber-attacks have been reported in the recent decade, affecting hundreds of thousands of people. These attacks can lead to large power system blackouts, and optimization models are essential tools for optimal decision-making in reliable and secure operation of cyber-physical power systems. In this paper, optimization models in cyber-physical power systems are extensively reviewed and classified based on their applications, including cyber-security and optimal operation. One major application of optimization is in cyber-security evaluation of smart grids. This paper investigates the models to implement cyber-attacks against state estimation, coordinated cyber-physical attacks aiming to cover each other, and financially-motivated attacks in electricity markets; optimal defense strategies and interactions between the attacker and the defender are also introduced. Furthermore, optimization models used in the operation and dispatching of cyber-physical power and energy systems, optimal routing of information networks, and privacy-preserving models are presented. Finally, as solving optimization models is a crucial step in optimal decision-making, solvers in the literature are also introduced.

Supporting Privacy-Preserving Big Data Analytics on Temporal Open Big Data

Nowadays, valuable big data are generated and collected rapidly from numerous rich data sources. Following the initiatives of open data, many organizations including municipal governments are willing to share their data such as open big data regarding parking violations. While there have been models to preserve privacy of sensitive personal data like patient data for health informatics, privacy of individuals who violated parking regulations should also be protected. Hence, in this article, we present a model for supporting privacy-preserving big data analytics on temporal open big data. This temporally hierarchical privacy-preserving model (THPPM) adapts and extends the traditional temporal hierarchy to generalize spatial data generated within a time interval with an aim to preserve privacy of individuals who violated parking regulations during some time intervals at certain geographic locations. Evaluation on open big data from two North American cities demonstrates the usefulness of our model in supporting privacy-preserving big data analytics on temporal open big data.

A privacy-preserving model for cloud data storage through fog computing

A privacy-preserving model for cloud data storage through fog computing

A privacy-preserving model for cloud data storage through fog computing

Nowadays, most of the organisations are shifting their data to the cloud platform because of its flexibility, elasticity, on-demand services, etc. The major concern of these organisations is to store the data on the cloud in a privacy-preserving manner as they lose the control rights, and the data can be leaked/tempered during the transmission. This paper presents a privacy preserving scheme that uses the Advanced Encryption Standard (AES) technique to store the client data on the cloud via fog computing. Encryption is performed at the local machine as well as fog server and then data is transferred to the cloud. Randomly generated files are used to perform the experiments and encryption/decryption time is computed. The results show an improvement of 80% and 88% when a file of 10 MB is encrypted and decrypted respectively as compared to the previous work.

Privacy-Preserving Aggregation for Federated Learning-Based Navigation in Vehicular Fog

Federated learning-based automotive navigation has recently received considerable attention, as it can potentially address the issue of weak global positioning system (GPS) signals under severe blockages, such as in downtowns and tunnels. Specifically, the data-driven navigation framework combines the position estimation offered by the high-sampling inertial measurement units and the position calibration provided by the low-sampling GPS signals. Despite its promise, the privacy preservation and flexibility of the participating users in the federated learning process are still problematic. To address these challenges, in this article, we propose an efficient, flexible, and privacy-preserving model aggregation scheme under a federated learning-based navigation framework named FedLoc. Specifically, our proposed scheme efficiently protects the locally trained model updates, flexibly supports the fluctuation of participants, and is robust against unregistered malicious users by exploiting a homomorphic threshold cryptosystem, together with the bounded Laplace mechanism and the skip list. We perform a detailed security analysis to demonstrate the security properties in terms of privacy preservation and dishonest user detection. In addition, we evaluate and compare the computational efficiency with two traditional schemes, and the simulation results show that our scheme greatly improves the computational efficiency during participant fluctuation. To validate the effectiveness of our scheme, we also show that only part of the model update is excluded from aggregation in the case of a dishonest user.

An Effective and Efficient Framework for Fast Privacy-Preserving Keyword Search on Encrypted Outsourced Cloud Data

Cloud providers offer storage as a service to the data owners to store emails and files on the cloud server. However, sensitive data should be encrypted before storing on the cloud server to avoid privacy concerns. With the encryption of documents, it is not feasible for data owners to retrieve documents based on keyword search as they can do with plain text documents. Hence, it is desirable to perform a multi-keyword search on encrypted data. To achieve this goal, we present a fast privacy-preserving model for keyword search on encrypted outsourced data in this paper. Specifically, the model first performs a keyword search on encrypted data and checks its support for dynamic operations. Based on keyword search results, it then sorts all the relevant data documents using the number of keywords matched for a given query. To evaluate its performance of our model, we applied the standard metrics like precision and recall. The results show the effectiveness of our privacy-preserving keyword search on encrypted outsourced data.

Personal phone number privacy-preserving models for public use

The importance of personal mobile numbers has dramatically increased in recent years. Most of social network’s apps today required a validated personal mobile number to register in their services. Publishing a person’s mobile number may lead to a privacy and security violation. In this paper, we describe how a person’s mobile number could easily be used to violate a user’s privacy. We study possible concerns and risks associated with publishing a user’s mobile number, and we propose an alternative: Virtual Mobile Number Model (VMNM) that links a user’s real mobile number with a virtual mobile number to help secure individual privacy. Telecommunication Service Provider (TSP) present privacy management system that sets up the connection between callers. Finally, we evaluate the model and explain how it helps to protect the user’s privacy as well as prevent personal data from being violated.

Privacy Preservation Models for Third-Party Auditor over Cloud Computing: A Survey

Cloud computing has become a prominent technology due to its important utility service; this service concentrates on outsourcing data to organizations and individual consumers. Cloud computing has considerably changed the manner in which individuals or organizations store, retrieve, and organize their personal information. Despite the manifest development in cloud computing, there are still some concerns regarding the level of security and issues related to adopting cloud computing that prevent users from fully trusting this useful technology. Hence, for the sake of reinforcing the trust between cloud clients (CC) and cloud service providers (CSP), as well as safeguarding the CC’s data in the cloud, several security paradigms of cloud computing based on a third-party auditor (TPA) have been introduced. The TPA, as a trusted party, is responsible for checking the integrity of the CC’s data and all the critical information associated with it. However, the TPA could become an adversary and could aim to deteriorate the privacy of the CC’s data by playing a malicious role. In this paper, we present the state of the art of cloud computing’s privacy-preserving models (PPM) based on a TPA. Three TPA factors of paramount significance are discussed: TPA involvement, security requirements, and security threats caused by vulnerabilities. Moreover, TPA’s privacy preserving models are comprehensively analyzed and categorized into different classes with an emphasis on their dynamicity. Finally, we discuss the limitations of the models and present our recommendations for their improvement.

Privacy-Preserving Distributed Multi-Task Learning against Inference Attack in Cloud Computing

Because of the powerful computing and storage capability in cloud computing, machine learning as a service (MLaaS) has recently been valued by the organizations for machine learning training over some related representative datasets. When these datasets are collected from different organizations and have different distributions, multi-task learning (MTL) is usually used to improve the generalization performance by scheduling the related training tasks into the virtual machines in MLaaS and transferring the related knowledge between those tasks. However, because of concerns about privacy breaches (e.g., property inference attack and model inverse attack), organizations cannot directly outsource their training data to MLaaS or share their extracted knowledge in plaintext, especially the organizations in sensitive domains. In this article, we propose a novel privacy-preserving mechanism for distributed MTL, namely NOInfer, to allow several task nodes to train the model locally and transfer their shared knowledge privately. Specifically, we construct a single-server architecture to achieve the private MTL, which protects task nodes’ local data even if n-1 out of n nodes colluded. Then, a new protocol for the Alternating Direction Method of Multipliers (ADMM) is designed to perform the privacy-preserving model training, which resists the inference attack through the intermediate results and ensures that the training efficiency is independent of the number of training samples. When releasing the trained model, we also design a differentially private model releasing mechanism to resist the membership inference attack. Furthermore, we analyze the privacy preservation and efficiency of NOInfer in theory. Finally, we evaluate our NOInfer over two testing datasets and evaluation results demonstrate that NOInfer efficiently and effectively achieves the distributed MTL.