Privacy Of Sensitive Data Research Articles

Client Selection for Federated Learning With Non-IID Data in Mobile Edge Computing

Federated Learning (FL) has recently attracted considerable attention in internet of things, due to its capability of enabling mobile clients to collaboratively learn a global prediction model without sharing their privacy-sensitive data to the server. Despite its great potential, a main challenge of FL is that the training data are usually non-Independent, Identically Distributed (non-IID) on the clients, which may bring the biases in the model training and cause possible accuracy degradation. To address this issue, this paper aims to propose a novel FL algorithm to alleviate the accuracy degradation caused by non-IID data at clients. Firstly, we observe that the clients with different degrees of non-IID data present heterogeneous weight divergence with the clients owning IID data. Inspired by this, we utilize weight divergence to recognize the non-IID degrees of clients. Then, we propose an efficient FL algorithm, named CSFedAvg, in which the clients with lower degree of non-IID data will be chosen to train the models with higher frequency. Finally, we conduct simulations using publicly-available datasets to train deep neural networks. Simulation results show that the proposed FL algorithm improves the training performance compared with existing FL protocol.

Privacy preserving classification over differentially private data

AbstractPrivacy preserving data classification is an important research area in data mining field. The goal of a privacy preserving classification algorithm is to protect the sensitive information as much as possible, while providing satisfactory classification accuracy. Differential privacy is a strong privacy guarantee that enables privacy of sensitive data stored in a database by determining the ratio of sensitive information leakage with respect to an ɛ parameter. In this study, our aim is to investigate the classification performance of the state‐of‐the‐art classification algorithms such as C4.5, Naïve Bayes, One Rule, Bayesian Networks, PART, Ripper, K*, IBk, and Random tree for performing privacy preserving classification. To preserve privacy of the data to be classified, we applied input perturbation technique coming from differential privacy, and observed the relationship between the ɛ parameter values and accuracy of the classifiers. To our best knowledge, this article is the first study that analyzes the performances of the well‐known classification algorithms over differentially private data, and discovers which datasets are more suitable for privacy preserving classification when input perturbation is applied to provide data privacy. The classification algorithms are compared by using the differentially private versions of the well‐known datasets from the UCI repository. According to the experimental results, we observed that, as ɛ parameter value increases, better classification accuracies are achieved with lower privacy levels. When the classifiers are compared, Naïve Bayes classifier is the most successful method. The ɛ parameter should be greater than or equal to 2 (i.e., ɛ ≥2) to achieve cloud server is malicious and untrusted, sensitive data will satisfactory classification accuracies.This article is categorized under: Commercial, Legal, and Ethical Issues > Security and Privacy Technologies > Classification

Applying Distributed Ledger Concepts to a Swiss Regional Label Ecosystem

Improving current supply chains by using distributed ledger technology (DLT) has been a highly researched topic during the last years. Currently, there are numerous articles elaborating on how such technologies can theoretically improve supply chains. However, case studies of such concepts and their economic value are scarce. In order to bridge this gap, we collaborated with a regional label company to clarify how a distributed ledger technology would benefit their ecosystem. This work answers the question of how such a prototype would look and whether it adds value. By following design science research practices, we design two artifacts based on requirements gathered in 14 interviews and discuss the artifacts’ elements within an evaluation panel. Our findings show that a distributed ledger application for the regional label ecosystem should have an open and decentralized architecture giving all participants full access to the shared data while still providing security and privacy for sensitive data. Additionally, data capturing should be simple. However, such an application does not add sufficient economic value and is currently of no practical interest in the regional label ecosystem as the expenditure likely exceeds the benefit.

Anonymous Message Authentication Scheme for Semitrusted Edge-Enabled IIoT

As internet of things and other technologies are widely used in industrial manufacturing, automation and intelligence have witnessed rapid developments, resulting in the proposal of the industrial internet of things (IIoT). However, the IIoT still faces various network security threats; hence, data integrity, confidentiality, and anonymity need to be ensured. The use of cloud and edge servers as semitrusted third parties often results in the leaking of privacy sensitive user data. Meanwhile, existing security schemes treat the cloud and edge as fully trusted entities, which is not always valid. Considering edge servers as semitrusted entities, we propose a novel message authentication scheme that leverages group signature technology and proxy reencryption technology to ensure data integrity, confidentiality, and anonymity. Through theoretical analysis and performance comparison, we prove the security of our scheme. In addition, we implement our scheme on a real publish/subscribe system, and the experimental results show the feasibility of our scheme.

Model validation and economic dispatch of a dual axis pv tracking system connected to energy storage with grid connection: A case of a healthcare institution in South Africa

Healthcare institutions, ranks the second highest energy intensive buildings in the commercial sector, with daily energy consumption ranging from 43 to 92 kWh per bed. Energy management in this sector may prove difficult due to the demand's critical and non-deferrable nature. Therefore, in this paper, a validated optimal power dispatch model of a proposed hybrid energy system connected to a healthcare institution is developed. The healthcare institution considered in this study, which will remain anonymous,11The healthcare institution considered in this paper is located in the Bloemfontein area and referred to as an anonymous healthcare entity in order to maintain confidentiality and privacy of sensitive data used in this study. is subjected to Time-of-Use (ToU) tariffs and maximum demand charges and is considering the implementation of renewable energy technologies to reduce energy costs. Consequently, given the geographical location of the building, a system consisting of a photovoltaic tracking system with a battery bank and grid connection supplying the load is proposed and modelled. The aim is to optimize the power flow between the hybrid system and battery in order to minimize the grid energy costs based on the ToU tariff while reducing the maximum demand charges from the utility. Annual potential cost savings of up to 40.9% were attained, while a projected break-even point of 7.1 years is noted with the proposed optimally controlled system as compared to the load exclusively supplied by the grid.

ABKS-SKGA: Attribute-based keyword search secure against keyword guessing attack

In order to guarantee security and privacy of sensitive data, attribute-based keyword search (ABKS) enables data owners to upload their encrypted data to cloud servers, and authorizes intended data users to retrieve it. Meanwhile, ABKS outsources heavy search work to cloud servers, which makes ABKS adaptive to mobile computing environment. However, as cloud servers can both generate keyword ciphertexts and run search algorithm, the existing most ABKS schemes are vulnerable to keyword guessing attack. In this paper, we show the fundamental cause that the existing ABKS schemes do not resist keyword guessing attack is any entity can generate keyword ciphertext. To solve the above problem, in the phase of keyword ciphertext generation, we use private key of data owner to sign keyword prior to generating keyword ciphertext. Therefore, any other entity does not forge keyword ciphertext, which can resist keyword guessing attack. We give the formal definition and security model of attributed-based keyword search secure against keyword guessing attack (ABKS-SKGA). Furthermore, we provide an ABKS-SKGA scheme. The ABKS-SKGA scheme is proved secure against chosen-plaintext attack (CPA). Performance analysis shows that the proposed scheme is practical.

Covert Communications in D2D Underlaying Cellular Networks With Power Domain NOMA

A device-to-device (D2D) communication link is vulnerable because it is relatively easy to be compromised by adversaries due to the fact that D2D terminals are power limited nodes. This article proposes a covert communication scheme that allows D2D communication links to transmit covert signals (e.g., privacy sensitive data) to ensure a low probability of detection. We allocate transmit powers of cellular and D2D noncovert signals following a fading D2D channel to add the uncertainty in adversary's background noises. With the help of base station, cooperative power domain nonorthogonal multiple access and successive interference cancellation are used to decode covert signal. Depending on whether a D2D transmitter has the knowledge of adversary's detection threshold, we derive minimum error probability to measure the covertness performance. Furthermore, we evaluate covert throughput, which is defined as a maximum average transmission rate of covert signal, subject to a given covertness performance.

Enabling ad-hoc reuse of private data repositories through schema extraction

BackgroundSharing sensitive data across organizational boundaries is often significantly limited by legal and ethical restrictions. Regulations such as the EU General Data Protection Rules (GDPR) impose strict requirements concerning the protection of personal and privacy sensitive data. Therefore new approaches, such as the Personal Health Train initiative, are emerging to utilize data right in their original repositories, circumventing the need to transfer data.ResultsCircumventing limitations of previous systems, this paper proposes a configurable and automated schema extraction and publishing approach, which enables ad-hoc SPARQL query formulation against RDF triple stores without requiring direct access to the private data. The approach is compatible with existing Semantic Web-based technologies and allows for the subsequent execution of such queries in a safe setting under the data provider’s control. Evaluation with four distinct datasets shows that a configurable amount of concise and task-relevant schema, closely describing the structure of the underlying data, was derived, enabling the schema introspection-assisted authoring of SPARQL queries.ConclusionsAutomatically extracting and publishing data schema can enable the introspection-assisted creation of data selection and integration queries. In conjunction with the presented system architecture, this approach can enable reuse of data from private repositories and in settings where agreeing upon a shared schema and encoding a priori is infeasible. As such, it could provide an important step towards reuse of data from previously inaccessible sources and thus towards the proliferation of data-driven methods in the biomedical domain.

Interoperability and Synchronization Management of Blockchain-Based Decentralized e-Health Systems

E-health systems have witnessed widespread usage in the last few years, mainly due to advancements in health monitoring hardware and the availability of remote diagnostic services. Given the numerous benefits, there are two main challenges: management of the e-health ecosystem and security and privacy of sensitive data. The former results from nonunified, redundant, and often replicated information across numerous independent e-health service providers. While the later stems from sensitive information stored in centralized systems that can be compromised. Blockchain has emerged as a promising technology, which can be used to secure access and privacy of data and provide an umbrella management solution to large-scale distributed and decentralized enterprise systems. In this article, we present a unified system for migrating independent conventional e-health systems to a single blockchain-based ecosystem. More specifically, we address the issues of difference in data structures for conventional relational databases and blockchain file databases. The solution describes the conversion process and synchronization of information in a unified system for large-scale e-health data. The implementation and analysis show that significant improvements in data storage, access control, and seamless migration can be achieved.

R²PEDS: A Recoverable and Revocable Privacy-Preserving Edge Data Sharing Scheme

Edge servers (ESs) are utilized to achieve the storage and sharing of IoT data. However, even if ES brings us much benefit, it also leads to many serious privacy leakage issues because users’ data in ESs are out of control. Moreover, ES providers may also disclose user’s private-sensitive data. Hence, in this article, we present a privacy-preserving, recoverable, and revocable edge data sharing scheme. In this scheme, we propose a novel attribute revocation chain based on the blockchain technology to achieve attribute revocation in ciphertext-policy attribute-based encryption (CP-ABE). Meanwhile, a secret sharing scheme (SSS) is introduced to assist the data recovery. Especially, for the situation that a single ES is hijacked, we also propose a corresponding efficient detection mechanism and key updating policy to promise the subsequent security of the whole system. Moreover, this scheme also resists Economic Denial-of-Sustainability (EDoS) attacks which are launched by some malicious users. The analysis shows that the proposed scheme can protect user’s privacy and resist many attacks. Additionally, relevant experimental results demonstrate that our scheme has low computational overhead on the user side.

Blockchain and federated learning-based distributed computing defence framework for sustainable society

Ensuring social security through the defense organization determines the creation of links between the army and society. Realizing the benefits of the Internet of Battle Things in the defense system can perfectly monetize intelligence and strengthen the armed forces. It establishes a network for strong connectivity in the army with good coordination between complex processes to effectively edge out the enemies. However, this new technology poses organizational and national security challenges that present both opportunities and obstacles. The current framework of the defense IoT network for sustainable society is not adequate enough to make actionable situational awareness decisions in order to infer the state of the battlefield while preserving the privacy of sensitive data. In this paper, we propose a distributed computing defence framework for sustainable society using the features of blockchain technology and federated learning. The proposed model presents an algorithm to meet the challenges of limited training data in order to obtain high accuracy and avoid a reason specific model. To evaluate the effectiveness of the proposed model, we prepare the dataset and investigate the performance of our framework in various scenarios. The result outcomes are promising in terms of accuracy and loss compared to baseline approach.

An Extensible and Effective Anonymous Batch Authentication Scheme for Smart Vehicular Networks

In recent years, research on the security of Industry 4.0 and the Internet of Things (IoT) has attracted a close attention from industry, government, and the scientific community. Smart vehicular networks, as a type of industrial IoT, inevitably exchange large amounts of security and privacy-sensitive data, which make them attractive targets for attackers. For protecting network security and privacy, we have proposed an extensible and effective anonymous batch authentication scheme. In contrast to traditional pseudonym authentication schemes, the same system private key need not to be preloaded in our scheme, effectively avoiding a system failure when destroying a vehicle. Besides, the certificate revocation list (CRL) size is merely related to the number of vehicles that have been revoked, regardless of the number of pseudonym certificates for revoked vehicles. Moreover, this scheme maintains the effectiveness of the traditional scheme, effectively reduces the scale of the CRL, and employs an identity revocation scheme that supports rapid distribution. The scheme supports conditional privacy protection, namely, only the trusted authority (TA) can uniquely trace and revoke vehicles. For illegal vehicles, the TA releases the two hashed seeds to facilitate traceability by all entities in its domain. Furthermore, security analysis indicates that our solution is secure under the random oracle model and fulfills a series of security requirements of vehicular networks. Compared to existing authentication schemes, performance evaluations show that the scheme offers relatively good performance in terms of time consumption.

Privacy Preserving for Sensitive Data using Data Masking Technique

In recent times, most the people are using internet where they are going to share sensitive information with other individual or with an organization like hospital, banking sector or business companies. So such huge amount of information will be stored on cloud. The attackers may try to hack the sensitive data and will try to misuse that data. So here the security for data comes first. There are numerous methods available to provide security for the data that is being shared among individuals or organizations. Most of the organizations take enough precautions to secure data that is shared with third party organizations. In recent times providing privacy for the sensitive data is high priority. The objective of this research is to discover the various data masking solutions for different applications for providing security to the data. Established data privacy method like AES or DES encryption technique proves to be proficient but time consuming. In order to avoid time consumption and to provide privacy for the data being shared, this paper proposes a information hiding method based on format-preserving encryption for sensitive data. This method will masquerade only sensitive data and make sure the encrypted data is still in the original format where it doesn’t consume much memory space. Organization like hospitals or banking sector or any business companies can use this format-preserving method to enhance the security of the data being shared. Tested the information on Spark illustrate that information hiding method based on format-preserving encryption can provide data privacy for sensitive data and preserve data format.

Local differential privacy for human-centered computing

Human-centered computing in cloud, edge, and fog is one of the most concerning issues. Edge and fog nodes generate huge amounts of data continuously, and the analysis of these data provides valuable information. But they also increase privacy risks. The personal sensitive data may be disclosed by untrusted third-party service providers, and the current solutions to privacy protection are inefficient, costly. It is difficult to obtain available statistics. To solve these problems, we propose a local differential privacy sensitive data collection protocol in human-centered computing. Firstly, to maintain high data utility, the selection of the optimal number of hash functions and the mapping length is based on the size of the collected data. Secondly, we hash the sensitive data, add the appropriate Laplace noise to the client side, and send the reports to the server side. Thirdly, we construct the count sketch matrix to obtain privacy statistics on the server side. Finally, the utility of the proposed protocol is verified by synthetic datasets and a real dataset. The experimental results demonstrate that the protocol can achieve a balance between data utility and privacy protection.

FloVasion: Towards Detection of non-sensitive Variable Based Evasive Information-Flow in Android Apps

ABSTRACT Smartphones are enriched by applications (apps) available through the mobile ecosystem. Various studies have reported that apps leaking sensitive user and device information are the primary target of cyber criminals. Existing program analysis tools can detect such information leakage flows. Reverse engineering tools are deployed to determine app information-flow via control and data-flow analysis. Malware authors employ information-flow based evasion techniques while leaking privacy sensitive data. In this paper, we discuss five novel app attacks that evade information flow analysis and leak sensitive device and user information (e.g. IMEI, SIM details, Location details, and user contacts). These attacks circumvent state-of-the-art analysis tools. We show that sensitive information can be leaked via non-sensitive variables, or by performing runtime inspection of classes and fields. We analyzed the proposed novel attack apps against some of the most promising state-of-the-art static analysis tools such as FlowDroid, DroidSafe, and dynamic analysis tools such as TaintDroid. Furthermore, we evaluated Play-Protect i.e. default on-device anti-malware, AVL Antivirus, and some other top commercial products against proposed novel app attacks. We demonstrate that existing tools are vulnerable to proposed attacks. Finally, this paper proposes AspectJ based runtime monitor as a possible solution that can be incorporated in the state-of-the-art app analysis techniques to detect information flow misuse.

Covert Communications in D2D Underlaying Cellular Networks With Antenna Array Assisted Artificial Noise Transmission

Due to its high speed and low latency, D2D communication plays an important role in providing proximity data services in 5G systems, which may contain privacy sensitive data. Covert communication is useful to protect the privacy of user data against adversaries. In a D2D underlaying cellular network, an antenna array can be used at a base station (BS) to transmit artificial noise to confuse adversaries that try to detect D2D covert signals. Based on the numbers of antennas at BS, two covert schemes are presented in this work and their performances are evaluated in terms of D2D covert throughput, i.e., maximum achievable D2D data rate with the given covertness requirements. As only channel distribution information (CDI) of adversary links is known to the BS, the average minimum error probability (AMEP) is used as a metric to measure the covertness performance. In the proposed schemes, closed-form expressions of the minimum AMEP and achievable D2D data rate are derived. It is shown that the derivation of minimum AMEP can be simplified if either one or massive antennas are allocated for sending artificial noise. The analytical results are compared to Monte-Carlo simulation results to verify the feasibility of the proposed schemes. It is also revealed that covert throughput can be further improved by setting system parameters properly, e.g., the number of antennas at BS and artificial noise transmit power.

Supply Chain Finance Innovation Using Blockchain

Blockchain, the underlying technology of digital currency, such as Bitcoin, has the characteristics of decentralization, stability, security, anonymity, and nontampering. Blockchain is being applied in an increasing number of fields. Supply chain finance is a financing model in which banks connect core enterprises with upstream and downstream enterprises to provide flexible financial products and services. In the traditional supply chain finance, the core enterprises with strong competitiveness and a large scale play an irreplaceable role in managing the supply chain information flow, logistics, and capital flow, which results in inequality and information asymmetry. Fraud in supply chain finance is also very serious. To solve the problems of the traditional supply chain finance, in this article, we build a new type of supply chain financial platform that uses blockchain technology to manage the whole process. This supply chain financial platform solves the problem of nontrust among the participants in the supply chain, improves the efficiency of the capital flow and information flow, reduces costs, and provides better financial services to the relevant parties in the supply chain. To protect users' privacy, we propose a new method of using homomorphic encryption in the blockchain to meet the needs of sensitive data privacy protection in supply chain financial scenarios.

A Privacy-Preserving Multi-Task Framework for Knowledge Graph Enhanced Recommendation

Multi-task learning (MTL) is a learning paradigm which can improve generalization performance by transferring knowledge among multiple tasks. Traditional collaborative filtering recommendation methods suffer from cold start, sparsity and scalability problems. The latest research has shown that applying side information of knowledge graph can not only solve the problems above, but also improve the accuracy of recommendation. However, existing multi-task methods for knowledge graph enhanced recommendation expose obvious issues of disclosing the private information of training samples. In order to solve these problems, we put forward a privacy-preserving multi-task framework for knowledge graph enhanced recommendation. In specific, Laplacian noise is added into the recommendation module to guarantee the privacy of sensitive data and knowledge graph is utilized to improve the accuracy of recommendation. Extensive experimental results on three datasets demonstrate that the proposed method can not only preserve the privacy of sensitive training data, but also have little effect on the prediction accuracy of the model.

Towards a Secure Internet of Things: A Comprehensive Study of Second Line Defense Mechanisms

The Internet of Things (IoT) exemplifies a large network of sensing and actuating devices that have penetrated into the physical world enabling new applications like smart homes, intelligent transportation, smart healthcare and smart cities. Through IoT, these applications have consolidated in the modern world to generate, share, aggregate and analyze large amount of security-critical and privacy sensitive data. As this consolidation gets stronger, the need for security in IoT increases. With first line of defense strategies like cryptography being unsuited due to the resource constrained nature, second line of defense mechanisms are crucial to ensure security in IoT networks. This paper presents a comprehensive study of existing second line of defense mechanisms for standardized protocols in IoT networks. The paper analyzes existing mechanisms in three aspects: Intrusion Detection Systems (IDS), Intrusion Prevention Systems (IPS) and Intrusion Response Systems (IRS). We begin by providing an overview of standardized protocol stack, its layers and defensive security systems in IoT. From there, we build our narrative by presenting an extended taxonomy of IDS, IPS and IRS classifying them on their techniques, deployment, attacks, datasets, evaluation metrics and data pre-processing methods. We then thoroughly review, compare and analyze the research proposals in this context, considering the unique characteristics involved in these systems. Based on the extensive analysis of the existing defensive security systems, the paper also identifies open research challenges and directions for effective design of such systems for IoT networks, which could guide future research in the area.

Federated Learning for Vehicular Internet of Things: Recent Advances and Open Issues.

Federated learning (FL) is a distributed machine learning approach that can achieve the purpose of collaborative learning from a large amount of data that belong to different parties without sharing the raw data among the data owners. FL can sufficiently utilize the computing capabilities of multiple learning agents to improve the learning efficiency while providing a better privacy solution for the data owners. FL attracts tremendous interests from a large number of industries due to growing privacy concerns. Future vehicular Internet of Things (IoT) systems, such as cooperative autonomous driving and intelligent transport systems (ITS), feature a large number of devices and privacy-sensitive data where the communication, computing, and storage resources must be efficiently utilized. FL could be a promising approach to solve these existing challenges. In this paper, we first conduct a brief survey of existing studies on FL and its use in wireless IoT. Then we discuss the significance and technical challenges of applying FL in vehicular IoT, and point out future research directions.