Privacy Preserving Research Articles

An Authentic-based Privacy Preservation System for Smart E-Healthcare Systems Based on Zero Run Length Encoding and DNA Cryptography

An Authentic-based Privacy Preservation System for Smart E-Healthcare Systems Based on Zero Run Length Encoding and DNA Cryptography

Privacy Challenges and Solutions in Big Data Analytics: A Comprehensive Review

Abstract: Large data collections with a more intricate and diversified structure are referred to as "big data." These traits are typically associated with more challenges when it comes to storing, analyzing, and applying additional procedures or getting results. The technique of analyzing vast quantities of intricate data to uncover patterns or connections that are concealed is known as "big data analytics." Nonetheless, there is a clear conflict between big data's extensive use and its security and privacy. This paper examines privacy needs in big data, distinguishes between privacy and security, and focuses on privacy and security issues in large data. This study addresses the applications of privacy in business by utilizing established techniques like HybrEx, k-anonymity, T-closeness, and L-diversity. Many privacy-preserving techniques have been created for protection of privacy at various phases of the big data life cycle (such as data generation, storage, and processing). This work aims to explain the issues facing current privacy preservation strategies in big data and to give a comprehensive evaluation of them. This study also introduces new approaches to privacy preservation in big data, such as quick anonymization of massive data streams, identity-based anonymization, differential privacy, privacy preserving big data publishing, and hiding a needle in a haystack. This study discusses big data privacy and security issues in healthcare. A comparative analysis of some contemporary large data privacy approaches is also conducted. A comparative analysis of the latest big data privacy approaches is also conducted.

Privacy-preserving federated machine learning modeling and predictive control of heterogeneous nonlinear systems

Privacy preservation in data-driven modeling of a heterogeneous nonlinear system with multiple subsystems has become vitally important since communication data is vulnerable to cyber-attacks. This work develops a federated learning (FL) modeling and model predictive control (MPC) method for heterogeneous nonlinear systems with multiple subsystems to address privacy preservation and heterogeneity issues. The FL framework with two different neural network structures is developed to aggregate the submodels trained locally for the subsystems into a global model without sharing the local data with each other. Subsequently, a theoretical bound on the generalization error of the FL models is established using information theory. The closed-loop stability criteria of heterogeneous nonlinear systems under the FL-based MPC scheme are developed in an information-theoretical manner. Finally, a chemical process network is applied to demonstrate the effectiveness of the proposed FL modeling and FL-based MPC methods.

A Confounding-Domain Randomized Approach for Providing Source Location Privacy Preservation for Wireless Sensor Networks

Wireless sensor networks (WSNs) have advanced technologically, allowing for a wide range of Internet of Things (IoT) applications. The Internet of Things (IoT) provides a platform for connecting items to achieve a specific goal with minimal human intervention. Various practical sectors, such as environmental monitoring and defense, demand IoT support with maximum object connectivity, and low human participation, yet face security concerns from strong unauthorized entities. As location privacy is one of these major vulnerabilities, continual monitoring of contextual information may lead the attacker to the asset's position. The location privacy of the source node that detects and reports the presence of an event is critical. In this study, we provide a source location privacy (SLP) preservation technique based on confounding domain angular routing (SLP-CDAR) that attempts to improve security while increasing network lifespan. To avoid traffic analysis attacks, packets first undergo a random walk, followed by a perplexing time domain routing that creates additional diversionary pathways. The packets are then routed via angle routing, followed by a random path, and finally delivered to the base station using the forward random walk technique. The experimental results prove that the proposed scheme enhances the location privacy strength while providing an improved network lifetime, and a swift increase in the entropy.

AURA-The Privacy Preserving Multifunctional Desktop Voice Assistant

Abstract: The “AURA” is the project which proposes the development of the versatile desktop voice assistant which mainly focuses on the privacy of the user.The convenience of voice interaction has surged in popularity, but concerns about user privacy remain. Conventional cloud-based voice assistants raise anxieties regarding data collection, storage, and potential misuse. This survey paper explores the burgeoning field of privacy-preserving desktop voice assistants powered by Artificial Intelligence (AI). We delve into the core challenges of on-device speech recognition, natural language understanding, and response generation while maintaining user privacy. We conclude by outlining open research questions and future directions for this evolving field, paving the way for the development of secure and user-centric voice interaction experiences on desktops.

Providing Highest Privacy Preservation Scenario for Achieving Privacy in Confidential Data

Providing Highest Privacy Preservation Scenario for Achieving Privacy in Confidential Data

Enhancing Federated Learning Evaluation: Exploring Instance-Level Insights with SQUARES in Image Classification Models

Federated Learning (FL) presents a novel approach within the domain of Machine Learning (ML)—enabling the training of ML models in a distributed manner. This paradigmatic shift ensures the preservation of user privacy by conducting the training process at the edge, where data remains localized on individual devices. This stands in contrast to the conventional centralized paradigm—where users transmit data to a central server for processing. The FL framework operates within a more heterogeneous environment characterized by diverse data distributions across clients, a departure from the engineer-analyzed datasets typical of centralized paradigms. Whereas, evaluation of FL models typically relies on statistical techniques such as accuracy, recall, precision, log loss, and the confusion matrix, alongside visualization methods. While these techniques provide an overview of the model's performance and data utilization—they may lack granularity when comparing models with disparate characteristics. However, the SQUARES technique, offers a more nuanced evaluation of model performance at the instance level. This approach facilitates the examination of data biases, outlier detection, and model behavior during training on individual samples. Therefore, this study presents the development and evaluation of an FL image classification model across various scenarios—utilizing the SQUARES prototype. In addressing these more intricate scenarios, we aim to augment traditional visualizations and metrics, thereby uncovering insights and nuances that may elude standard evaluation methods prevalent in ML benchmarks.

A novel intelligent approach for color image privacy preservation

A novel intelligent approach for color image privacy preservation

RSDA: A Reliable and Secure Data Aggregation Scheme for Smart Grid

Smart grids are modern power distribution systems that utilize advanced technologies to optimize energy generation, distribution, and consumption. The huge amount of data generated by various sources, such as smart meters, sensors, and other devices, can be aggregated for efficient energy management, supporting demand response etc. However, this data can contain sensitive information about individual’s energy usage patterns, behaviour, and preferences, which raises several privacy concerns. Data reliability is another major issue, as the data send from the smart meters to the aggregators may get corrupted due to errors introduced by the communication channel. In this paper, a private-key additive homomorphic encryption scheme based on polar codes is proposed for privacy preserving data aggregation. The proposed scheme not only ensures data confidentiality but also provide data reliability. The security of this scheme relies on the difficulty in decoding the codeword and is achieved by embedding security in the generator matrix and error vector. Security analysis shows that the proposed scheme is resistant against all known attacks against private-key code-based cryptosystems. The performance analysis is evaluated in terms of error performance, communication overhead and computational complexity. The performance comparison with related additive homomorphic encryption scheme shows the efficiency of the proposed scheme.

Measurement-device-independent quantum homomorphic encryption

Quantum homomorphic encryption allows a server to directly operate on the encrypted data, which has many applications in privacy preservation. There is an important problem in quantum homomorphic encryption: quantum states may be attacked by eavesdroppers during the transmission process, which gives rise to a wrong evaluation result obtained by the client. However, the problem has not been considered yet. In this letter, we firstly study how to deal with the problem and present a measurement-device-independent quantum homomorphic encryption scheme. Furthermore, this scheme can double the space distance for quantum transmission between client and server compared with the previous works. Additionally, we give some circuit simulations to verify the feasibility of the scheme.

Protecting Privacy in Surveillance Systems via Selective Video Encryption

The "Privacy Preservation in Surveillance Video Using Selective Encryption" study addresses the issue of privacy in surveillance videos. Video surveillance systems are widely deployed in many public places such as banks, supermarkets, airports, roads, and residential areas. However, the privacy of individuals in these videos is a major concern. The proposed system aims to conceal faces while not interfering with the observation and recognition of human activities. The system uses selective encryption to encrypt only the face region of the frames while other parts of the frame are retained as it is. The proposed method is reversible for revealing faces whenever needed to the authorized person using proper secret keys. The project also aims to ensure the security of the encryption algorithm used and provide a user-friendly interface for ease of use. Overall, this study aims to provide an efficient and scalable solution to the problem of privacy in surveillances.

Privacy Preserving Using K Member Gaussian Kernel Fuzzy C Means and Self Adaptive Honey Badger for Online Social Networks

An online social network (OSN) gives users a strong platform to communicate and exchange information. Protecting publicly published data from individual identification is the primary problem in sharing social network databases. The most popular method for protecting privacy is anonymizing data, which involves deleting or altering some information while maintaining as much of the original data as feasible. This work presents a combination anonymizing algorithm, which is based on k member Gaussian kernel fuzzy c means clustering and self-adaptive honey badger optimization technique (KGKFCM-SAHBO). As part of the suggested anonymization process, the various users are divided into C clusters, each of which has at least K users, using a K-member Gaussian kernel fuzzy c means clustering technique. After that, the primary clusters are further optimized using the self-adaptive honey badger optimization approach (SAHBO) to further anonymize the data and network graph. Using the Yelp dataset, the experimental findings demonstrate the efficiency of the proposed model and evaluate a number of parameters, including execution time, degree of anonymization, and information loss. The experimental results show that the proposed strategy reduced information loss and improved the degree of anonymization when compared to existing methodologies.

A smart agent-based approach for privacy preservation and threat mitigation to enhance security in the Internet of Medical Things

A smart agent-based approach for privacy preservation and threat mitigation to enhance security in the Internet of Medical Things

Context Privacy Preservation for User Validation by Wireless Sensors in the Industrial Metaverse Access System

The Industrial Metaverse provides unparalleled prospects for increasing productivity and efficiency across multiple sectors. As wireless sensor networks play an important role in data collection and transmission within this ecosystem, preserving context privacy becomes critical to protecting sensitive information. This paper investigates the issue of context privacy preservation for user validation via AccesSensor in the Industrial Metaverse and presents a technological method to address it. We explore the need for context privacy, look at existing privacy preservation solutions, and propose novel user validation methods that are customized to the Industrial Metaverse’s access system. This method is evaluated on time-based efficiency, privacy method and bandwidth utilization. Our method performs better as compared to the DPSensor. Our research seeks to provide insights and recommendations for developing strong privacy protection methods in wireless sensor networks that operate within the Industrial Metaverse ecosystem.

LSH Models in Federated Recommendation

Given the challenges in recommendation effectiveness, communication costs, and privacy issues associated with federated learning, the current algorithm amalgamates locality sensitive hash (LSH) with three federated recommendation models: Generalized Matrix Factorization, Multilayer Perceptions, and Neural Matrix Factorization. First, the participation weights of the model are determined based on the participation degree of the federated learning clients to improve the efficiency of joint learning. Second, the local parameters of the federated aggregation model are divided into two groups to protect user embedding. Finally, rapid mapping and similarity retrieval of the upload parameters are performed using LSH to protect user privacy and shorten training time. We conducted experiments to compare the performance differences between LSH-based and Laplace noise-based differential privacy methods in terms of recommendation effectiveness, communication costs, and privacy preservation. Experimental results demonstrate that LSH models achieved a favorable balance between recommendation effectiveness and privacy protection, with improved time performance.

Enhancing security and privacy in smart agriculture: A novel homomorphic signcryption system

Technology driven Smart Agriculture is transforming modern day farming practices through digital tools and real-time data analysis. It monitors plant health in both soil and soilless cultivation, promoting environmentally responsible practices by utilizing integrated sensors and precision methods. Despite the significant potential benefits, challenges persist in ensuring data security in the smart agriculture frameworks. The existing research has explored various mechanisms to cater these issues, yet these solutions susceptible to known attacks i.e., Confidentiality, Authentication, Privacy preservation. Notably, the available schemes in open literature face performance deficiencies due to an overreliance on Rivest-Shamir-Adleman (RSA), bilinear pairing, and elliptic curve (EC). To comprehensively address these challenges, this study presents a novel approach via employing homomorphic Signcryption based on Hyper-Elliptic Curves (HEC). Our HEC based Signcryption technique enhances security with lower computational cost and communication overhead as compared to the existing techniques. Furthermore, our solution provides the best performance in terms of efficiency, addressing the privacy preservation issues with conformance to the (Confidentiality, Integrity, and Availability) CIA triad. For proof of concept and correctness, we have validated the results in Scyther tool, with the assurance that proposed scheme is correct, verified, and resistant against known set of attacks. The proposed scheme achieves a remarkable reduction in both computational and communication costs around 95.08 % and 89.28 % respectively, enhancing practicality and suitability for real-world implementation. Thus, making it a suitable candidate for employing in smart agriculture environments, encompassing both soil and soilless cultivation scenarios. This research contributes a robust, secure, cost effective, and efficient solution to the challenges posed by the evolving landscape of agriculture, paving the way for enhanced data protection and system resilience in smart agriculture systems.

NHAPMAD: Novel hybrid approaches for privacy‐preserved multiple attacks detection

SummaryDetecting anomalies is crucial for maintaining security in Wireless Sensor Networks (WSNs), as they are susceptible to various attacks that compromise nodes and yield inaccurate outcomes. Conventional attack detection approaches face challenges like high false positives, vulnerability to complex attacks, and limited adaptability to changing attacks due to predefined patterns. Additionally, the computational strain on resource‐constrained nodes hampers network efficiency, demanding innovative and resilient security solutions. Therefore, this research work introduces Novel Hybrid Approaches for Privacy‐preserved Multiple Attacks Detection (NHAPMAD) framework in both network attack detection system and host attack detection system. This topology bolsters the network's defense against various types of attacks, thereby ensuring the preservation of sensitive data privacy. Federated learning has been incorporated into the NHAPMAD framework to protect user privacy in WSNs. The introduced framework provides better anomaly detection and reduces false alarms. Additionally, the introduced model protects sensitive data, ensuring the security and integrity of the entire WSN, promoting a stable and dependable operating environment. The introduced method exhibits superior performance across various metrics like overall accuracy (99.6%), F1‐score (99.59%), recall (99.47%), precision (99.63%), detection rate (99.5%), processing time (0.0009 s), etc. compared to traditional approaches, marking a significant advancement in the realm of WSN security.

Real-Time Human Pose Estimation Using Machine Learning

Human pose estimation is a pivotal domain within computer vision, underpinning applications from motion capture in cinematic production to sophisticated user interfaces in desktop devices. This research delineates the implementation of real-time human pose estimation within web browsers utilizing TensorFlow.js and the PoseNet model. PoseNet, an advanced machine learning model optimized for browser-based execution, facilitates precise pose detection sans specialized hardware. The primary aim of this study is to integrate PoseNet with TensorFlow.js, achieving efficient real-time pose estimation directly in the browser by leveraging JavaScript, thereby ensuring seamless user interaction and broad accessibility. A modular system architecture is designed, focusing on optimization strategies such as model quantization, asynchronous processing, and on-device computation to enhance performance and privacy preservation. In conclusion, this research establishes a robust framework for deploying PoseNet in web environments, underscoring its potential to revolutionize human-computer interaction within browser-based applications. Our findings contribute significantly to the field of computer vision and machine learning, offering insights into the practical deployment of pose estimation models on widely accessible platforms. Keywords — ReaReal-time Pose Estimation, TensorFlow.js, PoseNet, Machine Learning, Computer Vision, Browser-based Pose Detection, Human-Computer Interaction, Multi-person Tracking, On-device Computation, Asynchronous Processing, Cross-browser Compatibility, Performance Optimization, Privacy-preserving AI, Web-based Machine Learning, Motion Capture, Fitness Tracking, Interactive , Virtual Reality Interfaces, Deep LearningLearning

A deep learning based approach for image retrieval extraction in mobile edge computing

AbstractDeep learning has been widely explored in 5G applications, including computer vision, the Internet of Things (IoT), and intermedia classification. However, applying the deep learning approach in limited-resource mobile devices is one of the most challenging issues. At the same time, users’ experience in terms of Quality of Service (QoS) (e.g., service latency, outcome accuracy, and achievable data rate) performs poorly while interacting with machine learning applications. Mobile edge computing (MEC) has been introduced as a cooperative approach to bring computation resources in proximity to end-user devices to overcome these limitations. This article aims to design a novel image reiterative extraction algorithm based on convolution neural network (CNN) learning and computational task offloading to support machine learning-based mobile applications in resource-limited and uncertain environments. Accordingly, we leverage the framework of image retrieval extraction and introduce three approaches. First, privacy preservation is strict and aims to protect personal data. Second, network traffic reduction. Third, minimizing feature matching time. Our simulation results associated with real-time experiments on a small-scale MEC server have shown the effectiveness of the proposed deep learning-based approach over existing schemes. The source code is available here: https://github.com/jamalalasadi/CNN_Image_retrieval.

An Effective Clustering Based Privacy Preserving Model Against Feature Attacks

The rise in healthcare-related illnesses has generated a substantial amount of patient data, making the safeguarding of patient data privacy imperative. Existing privacy protection methods face challenges, including longer execution times, compromised data quality, and increased information loss as data dimensions expand. Effective attribute selection is vital to enhance preservation methods. Our research introduces a privacy-preserving clustering approach that addresses these concerns through two stages: feature selection and anonymization. The first stage selects relevant features using symmetrical uncertainty (SU) and eliminates duplicates with Kendall’s Tau Correlation Coefficient. The Utility Preserved Anonymization (UPA) algorithm is employed in the second phase to achieve privacy preservation. Additionally, our approach reduces data dimensionality to simplify cluster creation for anonymization. Experimental analysis on real-time data demonstrates the strategy’s effectiveness, with outstanding sensitivity (97.85%) and accuracy (95%), efficiently eliminating unnecessary features and simplifying clustering complexity.