Level Of Privacy Protection Research Articles

Performance-Enhanced Federated Learning With Differential Privacy for Internet of Things

Federated learning (FL), which enables multiple distributed devices (clients) to collaboratively train a global model without transmitting their private data, has attracted much attention in the Internet of Things (IoT) domain. Compared with centralized learning, FL has obvious privacy advantages because it can protect the clients’ raw data from direct access by adversaries. Furthermore, to prevent the adversaries from inferring private information from the transmitted parameters, several FL algorithms based on differential privacy (DP) have been proposed, where the clients add artificial noise to their local parameters for privacy protection. Nevertheless, the added noise would disrupt the learning process and degrade the performance of the trained model. Considering this, in this article, we develop a performance-enhanced DP-based FL (PEDPFL) algorithm, where a classifier-perturbation regularization method is proposed to improve the robustness of the trained model against DP-injected noise. We derive the theoretical privacy and convergence analysis of the proposed algorithm, and also demonstrate the influence of some hyperparameters on the convergence performance. Simulation results on real-world data sets show that the proposed algorithm has better classification performance than the existing DP-based FL algorithms at the same level of privacy protection, and thus, it is more applicable to IoT applications.

The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization

Abstract We present a novel benchmark and associated evaluation metrics for assessing the performance of text anonymization methods. Text anonymization, defined as the task of editing a text document to prevent the disclosure of personal information, currently suffers from a shortage of privacy-oriented annotated text resources, making it difficult to properly evaluate the level of privacy protection offered by various anonymization methods. This paper presents TAB (Text Anonymization Benchmark), a new, open-source annotated corpus developed to address this shortage. The corpus comprises 1,268 English-language court cases from the European Court of Human Rights (ECHR) enriched with comprehensive annotations about the personal information appearing in each document, including their semantic category, identifier type, confidential attributes, and co-reference relations. Compared with previous work, the TAB corpus is designed to go beyond traditional de-identification (which is limited to the detection of predefined semantic categories), and explicitly marks which text spans ought to be masked in order to conceal the identity of the person to be protected. Along with presenting the corpus and its annotation layers, we also propose a set of evaluation metrics that are specifically tailored toward measuring the performance of text anonymization, both in terms of privacy protection and utility preservation. We illustrate the use of the benchmark and the proposed metrics by assessing the empirical performance of several baseline text anonymization models. The full corpus along with its privacy-oriented annotation guidelines, evaluation scripts, and baseline models are available on: https://github.com/NorskRegnesentral/text-anonymization-benchmark.

An adaptive decentralized regulation strategy for the cluster with massive inverter air conditionings

To deal with the power fluctuation caused by renewable energy integration and load growth, it has been a general recognition to provide regulation services for local power system or main grid by flexible loads. There is a certain range of adaption to temperature for users and thermal inertias for building components, making it possible for air conditioning (AC) loads to participate in demand response (DR). Large cluster of ACs offers a resource akin to that of a distributed energy storage system, which is also an important regulation module of virtual power plant (VPP). Inverter air conditioning (IAC) is gradually occupying the market proportion owing to comfort and power savings. It has become a key technology in the new power system on how to coordinate massive IAC resources with heterogeneous parameters and status to output reliable load regulation services. To this end, this paper proposes a consensus control strategy for the IACs cluster based on lightweight decentralized architecture. The task is distributed fairly while ensuring the occupants’ comfort. The target load curve can be accurately tracked with high adaptability and robustness. The interactive parameters are generated from the bottom up based on individuals’ response ability, which facilitates rapid convergence. Together with the intrinsic adaptability and robustness, the hosting mechanism for the coordinator is designed to guarantee high fault-tolerance, and therefore plug-and-play can be satisfied. Besides, dimensionality reduction and locality for the interaction data ensure a higher level of privacy protection. The advantages are illustrated in case studies and compared with other approaches. To the best of our knowledge, the proposed method has the overwhelming convergence performance over the present literatures. These characteristics indicate a sufficient basis for its application in the variable conditions with massive users and can be extended to more scenarios using consensus control.

MAPP: An efficient multi-location task allocation framework with personalized location privacy-protecting in spatial crowdsourcing

Due to its wide coverage and strong scalability, spatial crowdsourcing (SC) has become a research hotspot in recent years. In order to assign tasks to closer workers, it is necessary for workers to provide accurate locations to the server. However, it will result in the leakage of the participants’ location privacy. Existing works provide each worker with the same level of location privacy protection, which cannot meet the different privacy requirements of various workers. In addition, most works assume that the tasks are single-location tasks, and do not consider multi-location tasks. In this paper, we propose the Multi-location Task Allocation Problem with personalized location privacy protection (MLTAP). As far as we know, we are the first to study MLTAP. We propose a Multi-location task Allocation framework with Personalized location Privacy-protecting (MAPP). In order to allocate tasks efficiently, we use the R-tree to store workers and minimum bounding rectangle to represent multi-location tasks, thus filtering the unreachable workers for tasks. To better eliminate the adverse effect of location confusion, the SC server sorts candidate workers by the ranking metrics and allocates multi-location tasks efficiently. Finally, we conduct experiments to verify that MAPP has good performance in terms of utility.

A renewable energy microgrids trading management platform based on permissioned blockchain

This paper presents an energy trading platform based on the permissioned blockchain for managing renewable energy microgrids. To accomplish low-cost and efficient renewable energy trading, a series of automated trading processes is designed for the trading platform, including the token trading mechanism and account management mechanism. Meanwhile, we actualise set of trading processes in the trading platform using smart contract and use the Internet of Things technology to facilitate the automatic execution of trading. Besides, we devised a homomorphic encryption scheme that provides an exceptional level of privacy protection without compromising trading efficiency to better safeguard users' privacy in the trading platform. Therefore, utilising the trading management platform for renewable energy we developed can increase user participation in trading. Finally, the proposed trading management platform has been constructed and deployed utilising the permissioned blockchain Hyperledger Fabric, and the effect of the homomorphic encryption scheme and the trading process has been tested. The simulation results demonstrate the practicability of the designed renewable energy trading management platform.

Tight differential privacy blanket for shuff model

With the recent bloom of focus on digital economy, the importance of personal data has seen a massive surge of late. Keeping pace with this trend, the model of data market is starting to emerge as a process to obtain high-quality personal information in exchange of incentives. To have a formal guarantee to protect the privacy of the sensitive data involved in digital economy, \emph{differential privacy (DP)} is the go-to technique, which has gained a lot of attention by the community recently. However, it is essential to optimize the privacy-utility trade-off by ensuring the highest level of privacy protection is ensured while preserving the utility of the data. In this paper, we theoretically derive sufficient and necessary conditions to have tight $(\epsilon,\,\delta)$-DP blankets for the shuffle model, which, to the best of our knowledge, have not been proven before, and, thus, characterize the best possible DP protection for shuffle models which can be implemented in data markets to ensure privacy-preserving trading of digital economy.

Differential Privacy via Haar Wavelet Transform and Gaussian Mechanism for Range Query.

Range query is the hot topic of the privacy-preserving data publishing. To preserve privacy, the large range query means more accumulate noise will be injected into the input data. This study presents a research on differential privacy for range query via Haar wavelet transform and Gaussian mechanism. First, the noise injected into the input data via Laplace mechanism is analyzed, and we conclude that it is difficult to judge the level of privacy protection based on the Haar wavelet transform and Laplace mechanism for range query because the sum of independent random Laplace variables is not a variable of a Laplace distribution. Second, the method of injecting noise into Haar wavelet coefficients via Gaussian mechanism is proposed in this study. Finally, the maximum variance for any range query under the framework of Haar wavelet transform and Gaussian mechanism is given. The analysis shows that using Haar wavelet transform and Gaussian mechanism, we can preserve the differential privacy for each input data and any range query, and the variance of noise is far less than that just using the Gaussian mechanism. In an experimental study on the dataset age extracted from IPUM's census data of the United States, we confirm that the proposed mechanism has much smaller maximum variance of noises than the Gaussian mechanism for range-count queries.

Cross-Layer Device Authentication With Quantum Encryption for 5G Enabled IIoT in Industry 4.0

Industrial Internet of Things (IIoT), a core enabler of Industry 4.0, is evolving rapidly to tackle the challenges imposed by explosive real-time manufacturing data in the context of Internet and telecommunication industry. 5G technology is the key to addressing such challenges. This is done by bypassing upper authentication protocols and supporting small data transmission during initial access, which, however, causes serious security breaches in IIoT device authentication. To solve this, in this article propose a secure cross-layer authentication framework based on quantum walk on circles. The system performs random hash coding on multidomain physical-layer resources to encode and decode device identifiers securely, while using a quantum walk based privacy-preserving protocol to maintain code privacy at arbitrary high level, being controlled by the number of occupied physical resources. The upper bound of decoding errors is derived and a nonconvex integer programming problem of minimizing the bound is formulated to characterize the security performance. The space of one-time keys for encryption is also derived that show how high privacy and scalability advantage is maintained against classical and quantum computers. Finally, we derive novel expressions of failure probability of this new authentication system and numerically show that our scheme can bring ultrahigh level of security and privacy protection with low latency despite attack.

DPCL: Contrastive representation learning with differential privacy

With the proliferation of unlabeled data, increasing efforts have been devoted to unsupervised learning. As one of the most representative branches of unsupervised learning, contrastive learning has made great progress with its high efficiency. Unfortunately, privacy threats to contrastive learning have become sophisticated, making it imperative to develop effective technologies that can deal with such threats. To alleviate the privacy issue in contrastive learning, we propose some novel techniques based on differential privacy, which aim at reducing the high sensitivity of gradient in the private training caused by interactive contrastive learning. Specifically, we add differentially private protection to the connection point related to different per-example gradients, which decreases the sensitivity of the gradients significantly. Our experiments on SimCLR and the Barlow Twins show that our approach is superior since it is more accurate while maintaining the same level of privacy protection.

Protection of gait data set for preserving its privacy in deep learning pipeline

Human gait is a biometric that is being used in security systems because it is unique for each individual and helps recognise one from a distance without any intervention. To develop such a system, one needs a comprehensive data set specific to the application. If this data set somehow falls in the hands of rogue elements, they can easily access the secured system developed based on the data set. Thus, the protection of the gait data set becomes essential. It has been learnt that systems using deep learning are easily prone to hacking. Hence, maintaining the privacy of gait data sets in the deep learning pipeline becomes more difficult due to adversarial attacks or unauthorised access to the data set. One of the popular techniques for stopping access to the data set is using anonymisation. A reversible gait anonymisation pipeline that modifies gait geometry by morphing the images, that is, texture modifications, is proposed. Such modified data prevent hackers from making use of the data set for adversarial attacks. Nine layers were proposedto effect geometrical modifications, and a fixed gait texture template is used for morphing. Both these modify the gait data set so that any authentic person cannot be identified while maintaining the naturalness of the gait. The proposed method is evaluated using the similarity index as well as the recognition rate. The impact of various geometrical and texture modifications on silhouettes have been investigated to identify the modifications. The crowdsourcing and machine learning experiments were performed on the silhouette for this purpose. The obtained results in both types of experiments showed that texture modification has a stronger impact on the level of privacy protection than geometry shape modifications. In these experiments, the similarity index achieved is above 99%. These findings open new research directions regarding the adversarial attacks and privacy protection related to gait recognition data sets.

A Survey of Dummy-Based Location Privacy Protection Techniques for Location-Based Services.

As smart devices and mobile positioning technologies improve, location-based services (LBS) have grown in popularity. The LBS environment provides considerable convenience to users, but it also poses a significant threat to their privacy. A large number of research works have emerged to protect users’ privacy. Dummy-based location privacy protection solutions have been widely adopted for their simplicity and enhanced privacy protection results, but there are few reviews on dummy-based location privacy protection. Or, for existing works, some focus on aspects of cryptography, anonymity, or other comprehensive reviews that do not provide enough reviews on dummy-based privacy protection. In this paper, the authors provide a review of dummy-based location privacy protection techniques for location-based services. More specifically, the connection between the level of privacy protection, the quality of service, and the system overhead is summarized. The difference and connection between various location privacy protection techniques are also described. The dummy-based attack models are presented. Then, the algorithms for dummy location selection are analyzed and evaluated. Finally, we thoroughly evaluate different dummy location selection methods and arrive at a highly useful evaluation result. This result is valuable both to users and researchers who are studying this field.

Balancing data privacy and usability in the federal statistical system

The federal statistical system is experiencing competing pressures for change. On the one hand, for confidentiality reasons, much socially valuable data currently held by federal agencies is either not made available to researchers at all or only made available under onerous conditions. On the other hand, agencies which release public databases face new challenges in protecting the privacy of the subjects in those databases, which leads them to consider releasing fewer data or masking the data in ways that will reduce their accuracy. In this essay, we argue that the discussion has not given proper consideration to the reduced social benefits of data availability and their usability relative to the value of increased levels of privacy protection. A more balanced benefit–cost framework should be used to assess these trade-offs. We express concerns both with synthetic data methods for disclosure limitation, which will reduce the types of research that can be reliably conducted in unknown ways, and with differential privacy criteria that use what we argue is an inappropriate measure of disclosure risk. We recommend that the measure of disclosure risk used to assess all disclosure protection methods focus on what we believe is the risk that individuals should care about, that more study of the impact of differential privacy criteria and synthetic data methods on data usability for research be conducted before either is put into widespread use, and that more research be conducted on alternative methods of disclosure risk reduction that better balance benefits and costs.

The role of behavioural economics in shaping remedies for facebook's excessive data gathering

Currently, users disregard the low level of privacy protection and allow excessive data gathering by dominant online platforms. In return, they receive personalised social-media services from such companies. However, the fault is not entirely with consumers. This article aims to identify the circumstances that support excessive data gathering and argues that gatekeepers both exploit several heuristics that lead to cognitive biases and take advantage of the asymmetries of power and information confronting consumers. This article highlights the shift from neoclassical to behavioural economics and claims that the latter offers a convincing account of the situation consumers face in digital markets. By framing the problem as the exploitation of users’ behaviours, remedies can be formulated for the problem in question.

Privacy Protection and Intrusion Detection System of Wireless Sensor Network Based on Artificial Neural Network.

With the increasing openness and development of network technology, the network based on the wireless sensor network system has increasingly become an important tool for human social life and production, but it also brings some network security problems. Among them, focus is on network privacy disclosure and foreign intrusion and the research of intrusion detection and privacy protection has increasingly become an important topic of network security. This paper deeply studies the wireless sensor network system based on neural network on the basis of traditional privacy protection and intrusion detection system. Firstly, it applies particle swarm optimization algorithm and constructs a wireless sensor network intrusion detection system based on particle swarm optimization algorithm. The system includes important modules such as data extraction, data analysis, data feedback, and auxiliary decision-making. Compared with other algorithms, particle swarm optimization algorithm does not rely on problem information. It mainly uses real numbers to solve, so the algorithm has strong universality. At the same time, its corresponding principle is simple and easy to implement and less parameters need to be adjusted. Compared with other algorithms, particle swarm optimization algorithm has fast convergence speed and little memory requirement for the computer. At the same time, this paper uses the leap of particle swarm optimization algorithm to make it easier to find the global optimal solution. At the corresponding level of wireless sensor network privacy protection, based on the original data aggregation privacy protection scheme, this paper proposes a privacy protection scheme based on polynomial regression and a user privacy protection scheme based on the same state encryption, which further improves the security of privacy protection and facilitates the management of information. To realize the integrity of user privacy information protection, this paper realizes the decryption of data based on the correlation between binary metadata and compares the corresponding decrypted data with aggregated data, so as to complete the integrity of privacy data protection. The experimental results show that the binary metadata correlation decryption method proposed in this paper and the introduction of the corresponding particle swarm optimization algorithm improve the stability of the system by about 10%, the corresponding system security by a positive proportion, and the integrity of private data by about 10%; therefore, the algorithm proposed in this paper has obvious advantages.

USST: A two-phase privacy-preserving framework for personalized recommendation with semi-distributed training

Personalized recommendations are becoming indispensable for assisting online users in discovering items of interest. However, existing recommendation algorithms rely heavily on the collection of personal information, which poses significant privacy concerns to users. In this paper, we propose a two-phase privacy-preserving framework called user sampling and semi-distributed training (USST) for personalized recommendations, which can protect user privacy while ensuring high recommendation accuracy. In the USST framework, rather than directly training the model with all user records, a shared model is first trained with a small set of records contributed by sampled users (e.g., paid users and volunteers). This shared model is then distributed to each user, who further trains a personalized model using personal information. Thus, the USST guarantees that all unsampled users never disclose their private information. To validate the effectiveness and practicality of USST, we designed two USST-based privacy-preserving recommendation algorithms, USST-SVD and USST-NCF based on SVD and NCF algorithms, respectively. We conducted evaluations using MovieLens and Netflix Prize datasets, and the results show that, using only 20% of sampled users’ records, the recommendation accuracy of USST-based algorithms is very close to that of all users’ records. Thus, USST can significantly improve the level of privacy protection in recommender systems.

A Regulatory Game Analysis of Smart Aging Platforms Considering Privacy Protection.

Privacy and information protection are important issues in the era of big data. At present, China’s elderly care industry is gradually adopting the supply model of smart elderly care to alleviate the contradiction between supply and demand. However, the low level of regulation of smart aging platforms may lead to a low level of privacy protection on the platforms. Therefore, in this paper, based on the evolutionary game and Lyapunov theory, we discuss the willingness of elderly people to participate in regulation, the privacy protection status of platform service providers, and the degree of government regulation, as well as the key factors affecting the equilibrium of the three-party game system, and conduct simulation analysis and game system optimization using MATLAB. The simulation results show that and can be transformed to by adjusting the parameters, i.e., the optimal ESS is participation, high-quality protection, and low investment supervision; the service income of the elderly, the loss of privacy leakage, the investment cost of service providers, and the amount of government rewards and punishments are the key factors affecting the tripartite game system. By analyzing the impact of factors, such as benefits and costs, on privacy protection and the regulation of smart senior care platforms, the level of privacy protection of smart senior care platforms can be improved and the process of the comprehensive regulation of domestic senior care services can be promoted.

Security and Privacy-Enhanced Federated Learning for Anomaly Detection in IoT Infrastructures

Internet of Things (IoT) anomaly detection is significant due to its fundamental roles of securing modern critical infrastructures, such as falsified data injection detection and transmission line faults diagnostic in smart grids. Researchers have proposed various detection methods fostered by machine learning (ML) techniques. Federated learning (FL), as a promising distributed ML paradigm, has been employed recently to improve detection performance due to its advantages of privacy-preserving and lower latency. However, existing FL-based methods still suffer from efficiency, robustness, and security challenges. To address these problems, in this article, we initially introduce a blockchain-empowered decentralized and asynchronous FL framework for anomaly detection in IoT systems, which ensures data integrity and prevents single-point failure while improving the efficiency. Further, we design an improved differentially private FL based on generative adversarial nets, aiming to optimize data utility throughout the training process. To the best of our knowledge, it is the first system to employ a decentralized FL approach with privacy-preserving for IoT anomaly detection. Simulation results on the real-world dataset demonstrate the superior performance from aspects of robustness, accuracy, and fast convergence while maintaining high level of privacy and security protection.

DPVisCreator: Incorporating Pattern Constraints to Privacy-preserving Visualizations via Differential Privacy.

Data privacy is an essential issue in publishing data visualizations. However, it is challenging to represent multiple data patterns in privacy-preserving visualizations. The prior approaches target specific chart types or perform an anonymization model uniformly without considering the importance of data patterns in visualizations. In this paper, we propose a visual analytics approach that facilitates data custodians to generate multiple private charts while maintaining user-preferred patterns. To this end, we introduce pattern constraints to model users' preferences over data patterns in the dataset and incorporate them into the proposed Bayesian network-based Differential Privacy (DP) model PriVis. A prototype system, DPVisCreator, is developed to assist data custodians in implementing our approach. The effectiveness of our approach is demonstrated with quantitative evaluation of pattern utility under the different levels of privacy protection, case studies, and semi-structured expert interviews.

Private True Data Mining: Differential Privacy Featuring Errors to Manage Internet-of-Things Data

Available data may differ from true data in many cases due to sensing errors, especially for the Internet of Things (IoT). Although privacy-preserving data mining has been widely studied during the last decade, little attention has been paid to data values containing errors. Differential privacy, which is the de facto standard privacy metric, can be achieved by adding noise to a target value that must be protected. However, if the target value already contains errors, there is no reason to add extra noise. In this paper, a novel privacy model called true-value-based differential privacy (TDP) is proposed. This model applies traditional differential privacy to the “true value” unknown by the data owner or anonymizer but not to the “measured value” containing errors. Based on TDP, the amount of noise added by differential privacy techniques can be reduced by approximately 20% by our solution. As a result, the error of generated histograms can be reduced by 40.4% and 29.6% on average according to mean square error and Jensen–Shannon divergence, respectively. We validate this result on synthetic and five real data sets. Moreover, we proved that the privacy protection level does not decrease as long as the measurement error is not overestimated.

Preserving Location Privacy in the IoT against Advanced Attacks using Deep Learning

Location-based services (LBSs) have received a significant amount of recent attention from the research community due to their valuable benefits in various aspects of society. In addition, the dependency on LBS in the performance of daily tasks has increased dramatically, especially after the spread of the COVID-19 pandemic. LBS users use their real location to build LBS queries to take benefits. This makes location privacy vulnerable to attacks. The privacy issue is accentuated if the attacker is an LBS provider since all information about users is accessible. Moreover, the attacker can apply advanced attacks, such as map matching and semantic location attacks. In response to these issues, this work employs artificial intelligence to build a robust defense against advanced location privacy attacks. The key idea behind protecting the location privacy of LBS users is to generate smart dummy locations. Smart dummy locations are false locations with the same query probability as the real location, but they are far from both the real location and each other. Relying on the previous two conditions, the deep-learning-based intelligent finder ensures a high level of location privacy protection against advanced attacks. The attacker cannot recognize the dummies from the real location and cannot isolate the real location by a filtering process. In terms of entropy (the privacy protection metric), accuracy (the deep learning metric), and total execution time (the performance metric) and compared to the well-known DDA and BDA systems, the proposed system shows better results, where entropy = 15.9, accuracy = 9.9, and total execution time = 17 sec.