Privacy Leakage Problem Research Articles

RNC-DP: A personalized trajectory data publishing scheme combining road network constraints and GAN

The popularity of location-based services facilitates people’s lives to a certain extent and generates a large amount of trajectory data. Analyzing these data can contribute to society’s development and provide better location services for users, but it also faces the security problem of personal trajectory privacy leakage. However, existing methods often suffer from either excessive privacy protection or insufficient protection of individual privacy. Therefore, this paper proposes a personalized trajectory data publishing scheme combining road network constraints and GAN (RNC-DP). Firstly, after grid-representing the trajectory data, we remove the unreachable grids and define a trajectory generation constraint. Second, the proposed TraGM model synthesizes the trajectory data to meet the constraints. Again, during the trajectory data publishing process, the proposed TraDP mechanism performs k-means clustering on the synthesized trajectories and assigns appropriate privacy budgets to the clustered generalized trajectory location points. Finally, the protected trajectory data is published. Compared with the existing schemes, the proposed scheme improves privacy protection strength by 10.2%–41.2% while balancing data availability and has low time complexity.

Analysis of Personal Privacy Leakage under the Background of Digital Twin

With the development and application of digital twin technology, the problem of privacy leakage is becoming increasingly prominent. Privacy leakage issues caused by data abuse and weak awareness have attracted high attention. In this regard, this paper analyzes the causes of privacy leakage in the digital twin, analyzes the difficulties of privacy protection under the background of the digital twin, and puts forward the “legal co-governance model.” Through multi-party cooperation, improving the system, and improving literacy, people can effectively protect private information, ensure the security application of technology, law, and ethics, and provide a guarantee for the sustainable development and social application of digital twin technology.

Adaptive Privacy-Preserving Coded Computing with Hierarchical Task Partitioning.

Coded computing is recognized as a promising solution to address the privacy leakage problem and the straggling effect in distributed computing. This technique leverages coding theory to recover computation tasks using results from a subset of workers. In this paper, we propose the adaptive privacy-preserving coded computing (APCC) strategy, designed to be applicable to various types of computation tasks, including polynomial and non-polynomial functions, and to adaptively provide accurate or approximated results. We prove the optimality of APCC in terms of encoding rate, defined as the ratio between the computation loads of tasks before and after encoding, based on the optimal recovery threshold of Lagrange Coded Computing. We demonstrate that APCC guarantees information-theoretical data privacy preservation. Mitigation of the straggling effect in APCC is achieved through hierarchical task partitioning and task cancellation, which further reduces computation delays by enabling straggling workers to return partial results of assigned tasks, compared to conventional coded computing strategies. The hierarchical task partitioning problems are formulated as mixed-integer nonlinear programming (MINLP) problems with the objective of minimizing task completion delay. We propose a low-complexity maximum value descent (MVD) algorithm to optimally solve these problems. The simulation results show that APCC can reduce the task completion delay by a range of 20.3% to 47.5% when compared to other state-of-the-art benchmarks.

Decoupling Online Ride-Hailing Services: A Privacy Protection Scheme Based on Decentralized Identity

Online ride-hailing services have become a vital component of urban transportation worldwide due to their convenience and flexibility. However, the expansion of their user base has dramatically heightened the risks of user privacy information leakage. Among these risks, the privacy leakage problem caused by the direct correlation between user (driver and passenger) identity information and location-based ride information is of particular concern. This paper proposes a novel privacy protection scheme for ride-hailing services. In this scheme, decentralized identities are employed for user authentication, separating the identity registration service from the ride-hailing platform, thereby preventing the platform from obtaining user privacy data. The scheme also employs a fuzzy matching strategy based on location Points of Interest (POI) and a ciphertext-policy attribute-based hybrid encryption algorithm to hide the user’s precise location and restrict access to location information. Crucially, the scheme achieves the complete decoupling of identity registration services and location-based ride services on the ride-hailing platform, ensuring that users’ real identities and ride data cannot be directly associated, effectively protecting user privacy. Within the decoupled architecture, regulatory authorities are established to handle emergencies within ride-hailing services. Through simulation experiments and security analysis, this scheme is demonstrated to be both feasible and practical, providing a new privacy protection solution for the ride-hailing industry.

Efficient federated learning for pediatric pneumonia on chest X-ray classification

According to the World Health Organization (WHO), pneumonia kills about 2 million children under the age of 5 every year. Traditional machine learning methods can be used to diagnose chest X-rays of pneumonia in children, but there is a privacy and security issue in centralizing the data for training. Federated learning prevents data privacy leakage by sharing only the model and not the data, and it has a wide range of application in the medical field. We use federated learning method for classification, which effectively protects data security. And for the data heterogeneity phenomenon existing in the actual scenario, which will seriously affect the classification effect, we propose a method based on two-end control variables. Specifically, based on the classical federated learning FedAvg algorithm, we modify the loss function on the client side by adding a regular term or a penalty term, and add momentum after the average aggregation on the server side. The federated learning approach prevents the data privacy leakage problem compared to the traditional machine learning approach. In order to solve the problem of low classification accuracy due to data heterogeneity, our proposed method based on two-end control variables achieves an average improvement of 2% and an accuracy of 98% on average, and 99% individually, compared to the previous federated learning algorithms and the latest diffusion model-based method. The classification results and methodology of this study can be utilized by clinicians worldwide to improve the overall detection of pediatric pneumonia.

Edge computing in Internet of Vehicles: A federated learning method based on Stackelberg dynamic game

With the development of Intelligent Transportation Systems (ITS), data on the Internet of Vehicles (IoV) is increasing day by day. To alleviate computing pressure in IoV, Vehicle Edge Computing (VEC) is being widely used as a new computing paradigm. Moreover, to address the serious problem of privacy leakage in VEC, Federated Learning (FL) is increasingly considered for analyzing big data in VEC. However, in actual VEC, problems such as data heterogeneity and poor training often occur. To address this set of problems, we introduce a two-stage Stackelberg game structure for FL training, choosing the Cloud Server (CS) as the leader and the Roadside Unit (RSU) as the follower. Then, we define the utility functions of CS and RSU and obtain the optimal reward rate and local accuracy for each iteration. To address the problem of inefficiency during learning process, we separate high-dimensional data features into global features and personalized features based on feature separation, and use them to capture historical information. Next, vehicle federated learning with historical information based on dynamic Stackelberg game (VFLHI-DSG) was proposed. Finally, we conducted a comprehensive comparative experiment, results show that VFLHI-DSG has excellent performance in different scenarios.

Efficient Task Offloading for Mobile Edge Computing in Vehicular Networks

In vechcular networks, a promising approach to enhance vehicle task processing capabilities involves using a combination of roadside base stations or vehicles, there are two challenges when integrating the two offloading modeth: 1) the high mobility of vehicles can easily lead to connectivity interruptions between nodes, which in turn affects the processing of the tasks that are being offloaded; and 2) vehicles on the road are not completely trustworthy, and vehicle tasks that contain private information may suffer from result errors or privacy leakage and other problems. This paper investigates the computing offloading problem for minimizing task completion delay in vehicular networks. Specifically, we design a trust model for mobile in-vehicle networks and construct a migration decision problem to minimize the overall delay of task execution for all vehicle users. The simulation results show that the scheme proposed in this paper can effectively reduce the execution delay of the task compared to the baseline scheme.

Joint Optimization Algorithm for Latency-Energy and Privacy Combining Discrete Differential Evolution and Convex Optimization

A privacy protection task offloading algorithm combining discrete differential evolution and convex optimization is proposed to resolve the new position privacy leakage problem for mobile terminal due to transferring tasks to multiple edge servers for computation via wireless networks. First, the privacy cost of offloading decision is defined for the characteristics of the position privacy problem combined with the standard deviation theory. Second, the objective problem is modeled as a joint optimization of position privacy protection, offloading decision and transmission power, and the total cost of task offloading is an optimization objective. Finally, to handle the objective problem efficiently, offloading decision variable is decoupled from the transmission power variable to decrease the computational complexity of the problem; the discrete differential evolution algorithm is designed to accumulate the approximate optimal offloading decision, and the optimal transmission power is efficiently solved by variable substitution method and subgradient method. Simulations reveal that the algorithm has excellent convergence; it improves the position privacy protection level of mobile terminal and reduces the total cost of task offloading while maintaining lower energy consumption and latency.

A News Recommendation Method for User Privacy Protection

News recommendations play an important role in daily life, but there is a problem of privacy leakage. To address this problem, a news recommendation method for user privacy protection is proposed. It combines news recommendation with a federated learning framework to ensure accurate recommendations while protecting user privacy. To be specific, the method contains three key components: 1) It combines federated learning to ensure that user data is processed locally and not leaked to third parties, thus achieving privacy protection. 2) It fully considers the long-term and short-term interests of users and learns their short-term interests using the GRU model based on the item features of interaction, which provides a more comprehensive perspective on user modelling. 3) We design a score prediction method that fuses linear and nonlinear features to better capture the interaction between users and news and improve the accuracy of recommendation. The experimental validation on two public news datasets, Adressa and MIND, demonstrates that the method can still achieve efficient news recommendation without compromising user privacy.

Survey: federated learning data security and privacy-preserving in edge-Internet of Things

AbstractThe amount of data generated owing to the rapid development of the Smart Internet of Things is increasing exponentially. Traditional machine learning can no longer meet the requirements for training complex models with large amounts of data. Federated learning, as a new paradigm for training statistical models in distributed edge networks, alleviates integration and training problems in the context of massive and heterogeneous data and security protection for private data. Edge computing processes data at the edge layers of data sources to ensure low-data-delay processing; it provides high-bandwidth communication and a stable network environment, and relieves the pressure of processing massive data using a single node in the cloud center. A combination of edge computing and federated learning can further optimize computing, communication, and data security for the edge-Internet of Things. This review investigated the development status of federated learning and expounded on its basic principles. Then, in view of the security attacks and privacy leakage problems of federated learning in the edge Internet of things, relevant work was investigated from cryptographic technologies (such as secure multi-party computation, homomorphic encryption and secret sharing), perturbation schemes (such as differential privacy), adversarial training and other privacy security protection measures. Finally, challenges and future research directions for the integration of edge computing and federated learning are discussed.

DID-HVC-based Web3 healthcare data security and privacy protection scheme

In response to the current situation that Web2 Internet medical giants monopolize data elements and deprive medical users of their data rights and interests, self-sovereign identity(SSI) in the open environment of “Web3+Medicine” will make it possible for users to control and manage their e-medical data independently. However, SSI is a new identity management paradigm, and in the face of frequent interactions between identity credentials and application services, the existing research schemes have a coarse granularity of identity privacy protection, so there is an urgent need for attestation methods that selectively minimize the disclosure of identity attributes. In this study, we propose a SSI attribute selectively disclosable scheme based on a decentralized identifiers-hash verifiable credentials (DID-HVC) and design a model, that enables medical users not only to selectively minimize the disclosure of identity attribute data using verifiable credentials (VCs) with hash claims and combines with DID incorporating random obfuscation factors, to prevent overexposure of personal and healthcare privacy information, but also to safeguard users’ VCs are not linked and analysed. Finally, we provide a security and practicality analysis of our scheme and do simulation experiments based on Ethernet. The experimental results show that our scheme can more securely solve the problem of excessive privacy leakage of medical users within a feasible timeframe.

Privacy-protecting predictive cache method based on blockchain and machine learning in Internet of vehicles

To solve the privacy leakage problem faced by Internet of Vehicles (IoV) users when enjoying location-based services (LBS), a privacy-protecting predictive cache method based on blockchain and machine learning (BML-PPPCM) is proposed. First, a Bi-directional Long-Short Term Memory (Bi-LSTM) model is used to predict query requests over a future period based on historical request information. The predicted results are recommended to neighbors and broadcast to requestors. Then, deep Q-learning (DQN) is utilized to determine the optimal cache decision. Finally, a trust mechanism is introduced to calculate trust values, and blockchain is used to store transaction data and trust data, preventing malicious tampering by attackers. The simulation results show that BML-PPPCM has a higher cache hit ratio than other similar schemes and performs well in privacy protection and suppression of malicious and incentive denial of service providers.

PPIDSG: A Privacy-Preserving Image Distribution Sharing Scheme with GAN in Federated Learning

Federated learning (FL) has attracted growing attention since it allows for privacy-preserving collaborative training on decentralized clients without explicitly uploading sensitive data to the central server. However, recent works have revealed that it still has the risk of exposing private data to adversaries. In this paper, we conduct reconstruction attacks and enhance inference attacks on various datasets to better understand that sharing trained classification model parameters to a central server is the main problem of privacy leakage in FL. To tackle this problem, a privacy-preserving image distribution sharing scheme with GAN (PPIDSG) is proposed, which consists of a block scrambling-based encryption algorithm, an image distribution sharing method, and local classification training. Specifically, our method can capture the distribution of a target image domain which is transformed by the block encryption algorithm, and upload generator parameters to avoid classifier sharing with negligible influence on model performance. Furthermore, we apply a feature extractor to motivate model utility and train it separately from the classifier. The extensive experimental results and security analyses demonstrate the superiority of our proposed scheme compared to other state-of-the-art defense methods. The code is available at https://github.com/ytingma/PPIDSG.

Location privacy protection method based on differential privacy in crowdsensing task allocation

With the widespread popularity of smart phones, watches and other devices, mobile crowdsensing (MCS) has gradually entered the public’s field of vision. However, the widespread use of MCS technology is accompanied by an increasing risk of workers’ personal privacy being violated. Typically, workers are required to submit location information in order to participate in task assignments, and the privacy of a worker’s location information is a key factor in determining worker participation. Therefore, in order to solve the problem of workers location privacy leakage in the process of task allocation, this paper proposes a location privacy protection method based on local differential privacy (VLDPP). VLDPP constructs a task map based on Voronoi diagram according to the task location, and each task location is mapped into a task area to hide the task location. A local coordinate system is constructed based on the task area, and all workers in the area have their relative location coordinates recalculated and encoded, and then the encoding is perturbed by local differential privacy, thus ensuring workers location privacy. The worker uploads the perturbed location information to the server, which determines the workers in the task by calculating the worker’s acceptance rate and completes the task allocation. In addition, this paper improves the availability of perturbed worker location information by dividing the task area at a secondary level. This paper uses the internationally recognized World Check-In Gowalla dataset for experimental evaluation, which shows that the proposed method has good performance in terms of data availability and efficiency, providing adequate privacy guarantees.

Asynchronous Federated Learning: Methods and applications

Federated Learning (FL) is a distributed alternative to traditional machine learning frameworks that computes a global model on a centralized aggregation server according to the parameters of local models, which can address the privacy leakage problem caused by collecting sensitive data from local devices. However, the classic FL methods with synchronous aggregation strategies, in many cases, shall suffer from limitations in resource utilization due to the need to wait for slower devices (stragglers) to aggregate during each training epoch. In addition, the accuracy of the global model can be affected by the uneven distribution of data among unreliable devices in real-world scenarios. Therefore, many Asynchronous Federated Learning (AFL) methods have been developed on many occasions to improve communication efficiency, model performance, privacy, and security. This article elaborates on the existing research on AFL and its applications in many areas. The paper first introduces the concept and development of FL, and then discusses in detail the related work and main research directions of AFL, including dealing with stragglers, staleness, communication efficiency between devices, and privacy and scalability issues. Then, this paper also explores the application of AFL in different fields, especially in the fields of mobile device edge computing, Internet of Things devices, and medical data analysis. Finally, the article gives some outlook on future research directions and believes that it is necessary to design efficient asynchronous optimization algorithms, reduce communication overhead and computing resource usage, and explore new data privacy protection methods.

Federated Medical Learning Framework Based on Blockchain and Homomorphic Encryption

Federated learning-based medical data privacy sharing can promote the development of medical industry intelligence, but limited by its own security and privacy deficiencies, federated learning still suffers from a single point of failure and privacy leakage of intermediate parameters. To address these problems, this paper proposes a privacy protection framework for medical data based on blockchain and cross-silo federated learning, using cross-silo federated learning to establish a collaborative training platform for multiple medical institutions to enhance the privacy of medical data, introducing blockchain and smart contracts to realize decentralized federated learning to enhance trust between distrustful medical institutions and solve the problem of a single point of failure. In addition, a secure aggregation scheme is designed using threshold homomorphic encryption to prevent the privacy leakage problem during parameter transmission. The experimental and analytical results show that the accuracy of this paper’s scheme is consistent with the original federated learning scheme, effectively deals with the problems of single-point failure and inference attacks of federated learning, improves system robustness, and is suitable for medical scenarios with more stringent requirements on security and accuracy.

Enhanced Privacy Preservation and Data Storage in Blockchain-Based Electric Vehicle Network

Electric and autonomous vehicles (EV and AV) are spreading quickly on the road and producing extensive amounts of data that must be stored and retrieved securely. The ultimate goal of collecting these data is to feed machine learning models and make predictions to improve the traffic system, increase road safety, and save lives. Existing systems impose the problem of privacy leakage, storage space, and operating cost. They are causing panic among data owners and restricting them from sharing their data. This work presents a proposed solution that utilizes blockchain technology to tackle the aforementioned challenges. The proposed approach incorporates differential privacy and data compression methods to address privacy leaks and data storage space difficulties. Additionally, it aims to enhance the resistance of machine learning models against privacy attacks. By leveraging the features of blockchain, data stored on the blockchain becomes temper proof and protected against a single point of failure. Simulation results and numerical analysis show that the proposed methodology reduces data storage space requirements and improves privacy preservation.

An electronic medical record access control model based on intuitionistic fuzzy trust

Electronic Medical Records (EMR), as the core data of medical big data, has improved the efficiency of medical services in the process of sharing and use, but a series of data privacy leakage problems have emerged. Access control technology can ensure users' legitimate and appropriate access to data resources, but traditional access control has many limitations such as static and coarse-grained, which is difficult to meet in the dynamic and complex healthcare environment. We create a model to solve the privacy leakage problem of healthcare big data. The model utilizes the Latent Delicacy Allocation (LDA) topic model to quickly search documents and extract the topic probability distributions between the target patient and other patients' electronic medical records, which improves the efficiency of medical record document analysis; Calculating physician access similarity, we quantify physician access behavior to more accurately describe physician access behavior in the form of data. We combined the intuitionistic fuzzy theory with the trust evaluation method to create a novel trust evaluation method-- Intuitionistic Fuzzy Trust Evaluation Method, which can reflect the uncertainty characteristics that exist in the physician's diagnostic and treatment process when quantifying the trust of the access by using this method, and it is more flexible and practical, which enhances the accuracy of the quantification of the trust. Improving the traditional trust aggregation method by adding a time window and time decay function, the optimized method improves the accuracy of trust aggregation, and the experimental results are more in line with the actual law. We created a new intuitionistic fuzzy trust access control model using a relative entropy-based intuitionistic fuzzy clustering algorithm and a reward and punishment mechanism to achieve adaptive and dynamic access control for physician access behavior. Experiments show that the access control model based on intuitionistic fuzzy trust proposed in this article achieves 95% correctness in identifying user access behaviors and 94.29% correctness in identifying excessive user access behaviors. Experiments have proved that this model has obvious advantages over other models in the process of privacy protection of electronic medical record systems and has certain control effects.

Personalized Privacy Protection Method for Sensitive Temporal Data

Crowd sensing, as a new paradigm for perception data collection, has been widely applied. However, in the process of constructing a knowledge graph for group intelligence perception networks, attackers can use the correlation of participant temporal data to reconstruct participant related information, resulting in privacy leakage. A participant sensitive temporal data privacy protection method(PSTDPP) based on localized differential privacy is proposed to address this issue. Firstly, we use a knowledge graph to construct a sensitive temporal data relationship network and explore the correlation between temporal data background knowledge. Secondly, by combining attention mechanisms and mutual information ideas, a privacy model for participant submitted data and an availability model for perceived data are constructed, and personalized local differential privacy is used to solve the problem of graph data availability under privacy budget constraints. The simulation results show that the proposed method can effectively prevent the privacy leakage problem of sensitive temporal data, and can achieve a good balance between privacy protection level and data availability.

Optimal operation of energy hub considering reward-punishment ladder carbon trading and electrothermal demand coupling

As the massive carbon emissions from the power system, the shift of the power system to low-carbon becomes inevitable. In this context, this paper proposes a Stackelberg game approach to develop the operational strategy of energy hubs, which considers the reward and punishment ladder carbon trading mechanism and the coupling of electrothermal demand. To avoid the fixed carbon price in the past and the neglect of the incentive space for carbon trading, a ladder carbon trading mechanism of rewards and punishments is introduced to effectively depict carbon trading costs. The electrothermal coupling of the demand side is incorporated into the Stackelberg game model, and the flexible consumption model of users participating in the integrated demand response is established. The above model is solved by combining heuristic algorithm with solver CPLEX, which can solve the data privacy leakage problem of both parties. Simulation results show that the strategy can bring economic benefits to energy hub operators and users. Carbon emissions across the system were reduced by 14.4 %. Users with electric heating equipment can fully improve the electric load and heat load adjustment level, and improve their economic benefits by 2.4 % at the cost of a 3.2 % increase in carbon emissions.