2P3FL:A Novel Approach for Privacy Preserving in Financial Sectors Using Flower Federated Learning

The increasing data pool in finance sectors forces machine learning(ML)to step into new complications.Banking data has significant financial implications and is confidential.Combining users data from several organizations for various banking services may result in various intrusions and privacy leakages.As a result,this study employs federated learning(FL)using a flower paradigm to preserve each organization’s privacy while collaborating to build a robust shared global model.However,diverse data distributions in the collaborative training process might result in inadequate model learning and a lack of privacy.To address this issue,the present paper proposes the imple-mentation of Federated Averaging(FedAvg)and Federated Proximal(FedProx)methods in the flower framework,which take advantage of the data locality while training and guaranteeing global convergence.Resultantly improves the privacy of the local models.This analysis used the credit card and Canadian Institute for Cybersecurity Intrusion Detection Evaluation(CICIDS)datasets.Precision,recall,and accuracy as performance indicators to show the efficacy of the proposed strategy using FedAvg and FedProx.The experimental findings suggest that the proposed approach helps to safely use banking data from diverse sources to enhance customer banking services by obtaining accuracy of 99.55%and 83.72%for FedAvg and 99.57%,and 84.63%for FedProx.

Privacy preserving supply chain quantity discount contract design

The development and deployment of privary preserving supply chain quantity discount contract design can allow supply chain collaborations to take place without revealing any participant＇s data to others, reaping the benefits of collaborations wbile avoiding the drawbacks of privacy information disclosure. First, secure multi-party computation protocols are applied in the joint-ordering policy between a single supplier and a single retailer, the joint-ordering policy can be conducted without disclosing private cost information of any of the other supply chain partners. Secondly, secure multi-party computation protocols are applied in the privacy preserving supply chain quantity discount contract design between a single supplier and a single retailer. The information disclosure analyses of the algorithm show that： the optimal quantity discount of the jointordering policy can be conducted without disclosing private cost information of any of the other supply chain partners; the above protocol can be implemented without mediators; the privacy preserving quantity discount algorithm can be mutually verifiable and has solved the problem of asymmetric information.

Privacy Preserving Image Encryption with Deep Learning Based IoT Healthcare Applications

Latest developments in computing and communication technologies are enabled the design of connected healthcare system which are mainly based on IoT and Edge technologies.Blockchain,data encryption,and deep learning(DL)models can be utilized to design efficient security solutions for IoT healthcare applications.In this aspect,this article introduces a Blockchain with privacy preserving image encryption and optimal deep learning(BPPIEODL)technique for IoT healthcare applications.The proposed BPPIE-ODL technique intends to securely transmit the encrypted medical images captured by IoT devices and performs classification process at the cloud server.The proposed BPPIE-ODL technique encompasses the design of dragonfly algorithm(DFA)with signcryption technique to encrypt the medical images captured by the IoT devices.Besides,blockchain(BC)can be utilized as a distributed data saving approach for generating a ledger,which permits access to the users and prevents third party’s access to encrypted data.In addition,the classification process includes SqueezeNet based feature extraction,softmax classifier(SMC),and Nadam based hyperparameter optimizer.The usage of Nadam model helps to optimally regulate the hyperparameters of the SqueezeNet architecture.For examining the enhanced encryption as well as classification performance of the BPPIE-ODL technique,a comprehensive experimental analysis is carried out.The simulation outcomes demonstrate the significant performance of the BPPIE-ODL technique on the other techniques with increased precision and accuracy of 0.9551 and 0.9813 respectively.

An Enhanced Privacy Preserving, Secure and Efficient Authentication Protocol for VANET

Vehicular ad hoc networks (VANETs) have attracted growing interest in both academia and industry because they can provide a viable solutionthat improves road safety and comfort for travelers on roads. However, wireless communications over open-access environments face many security andprivacy issues that may affect deployment of large-scale VANETs. Researchershave proposed different protocols to address security and privacy issues in aVANET, and in this study we cryptanalyze some of the privacy preservingprotocols to show that all existing protocols are vulnerable to the Sybilattack. The Sybil attack can be used by malicious actors to create fakeidentities that impair existing protocols, which allows them to imitate trafficcongestion or at worse cause an accident that may result in the loss of humanlife. This vulnerability exists because those protocols store vehicle identitiesin an encrypted form, and it is not possible to search over the encryptedidentities to find fake vehicles. This attack is serious in nature and veryprevalent for privacy-preserving protocols. To cope with this kind of attack,we propose a novel and practical protocol that uses Public key encryptionwith an equality test (PKEET) to search over the encrypted identities withoutleaking any information, and eventually eliminate the Sybil attack. Theproposed approach improves security and at the same time maintains privacyin VANET. Our performance analysis indicates that the proposed protocoloutperforms state-of-the-art protocols: The proposed beacon generation timeis constant compared to a linear increase in existing protocols, with beaconverification shown to be faster by 7.908%. Our communicational analysisshows that the proposed protocol with a beacon size of 322 bytes has the leastcommunicational overhead compared to other state-of-the-art protocols.

Privacy Preserving Demand Side Management Method via Multi-Agent Reinforcement Learning

The smart grid utilizes the demand side management technology to motivate energy users towards cutting demand during peak power consumption periods, which greatly improves the operation efficiency of the power grid. However, as the number of energy users participating in the smart grid continues to increase, the demand side management strategy of individual agent is greatly affected by the dynamic strategies of other agents. In addition, the existing demand side management methods, which need to obtain users’ power consumption information,seriously threaten the users’ privacy. To address the dynamic issue in the multi-microgrid demand side management model, a novel multi-agent reinforcement learning method based on centralized training and decentralized execution paradigm is presented to mitigate the damage of training performance caused by the instability of training experience. In order to protect users’ privacy, we design a neural network with fixed parameters as the encryptor to transform the users’ energy consumption information from low-dimensional to high-dimensional and theoretically prove that the proposed encryptor-based privacy preserving method will not affect the convergence property of the reinforcement learning algorithm. We verify the effectiveness of the proposed demand side management scheme with the real-world energy consumption data of Xi’an, Shaanxi, China. Simulation results show that the proposed method can effectively improve users’ satisfaction while reducing the bill payment compared with traditional reinforcement learning(RL) methods(i.e., deep Q learning(DQN), deep deterministic policy gradient(DDPG),QMIX and multi-agent deep deterministic policy gradient(MADDPG)). The results also demonstrate that the proposed privacy protection scheme can effectively protect users’ privacy while ensuring the performance of the algorithm.

An Overview of Privacy Preserving Schemes for Industrial Internet of Things

The concept of Internet of Everything is like a revolutionary storm,bringing the whole society closer together.Internet of Things(IoT)has played a vital role in the process.With the rise of the concept of Industry 4.0,intelligent transformation is taking place in the industrial field.As a new concept,an industrial IoT system has also attracted the attention of industry and academia.In an actual industrial scenario,a large number of devices will generate numerous industrial datasets.The computing efficiency of an industrial IoT system is greatly improved with the help of using either cloud computing or edge computing.However,privacy issues may seriously harmed interests of users.In this article,we summarize privacy issues in a cloud-or an edge-based industrial IoT system.The privacy analysis includes data privacy,location privacy,query and identity privacy.In addition,we also review privacy solutions when applying software defined network and blockchain under the above two systems.Next,we analyze the computational complexity and privacy protection performance of these solutions.Finally,we discuss open issues to facilitate further studies.

Novel Privacy Preserving Method of Countering the Threats from Priori Knowledge

Recently,many data anonymization methods have been proposed to protect privacy in the applications of data mining.But few of them have considered the threats from user's priori knowledge of data patterns.To solve this problem,a flexible method was proposed to randomize the dataset,so that the user could hardly obtain the sensitive data even knowing data relationships in advance.The method also achieves a high level of accuracy in the mining process as demonstrated in the experiments.

Research on Privacy Preserving Data Mining

In recent years,with the explosive development in Internet,data storage and data processing technologies,privacy preservation has been one of the greater concerns in data mining.A number of methods and techniques have been developed for privacy preserving data mining.This paper provided a wide survey of different privacy preserving data mining algorithms and analyzed the representative techniques for privacy preservation.The existing problems and directions for future research are also discussed.

A Survey on Recent Advances in Privacy Preserving Deep Learning

Deep learning based on neural networks has made new progress in a wide variety of domain,however,it is lack of protection for sensitive information.The large amount of data used for training is easy to cause leakage of private information,thus the attacker can easily restore input through the representation of latent natural language.The privacy preserving deep learning aims to solve the above problems.In this paper,first,we introduce how to reduce training samples in order to reduce the amount of sensitive information,and then describe how to unbiasedly represent the data with respect to specific attributes,clarify the research results of other directions of privacy protection and its corresponding algorithms,summarize the common thoughts and existing problems.Finally,the commonly used datasets in the privacy protection research are discussed in this paper.

Privacy Preserving Solution for the Asynchronous Localization of Underwater Sensor Networks

Location estimation of underwater sensor networks(USNs)has become a critical technology,due to its fundamental role in the sensing,communication and control of ocean volume.However,the asynchronous clock,security attack and mobility characteristics of underwater environment make localization much more challenging as compared with terrestrial sensor networks.This paper is concerned with a privacy-preserving asynchronous localization issue for USNs.Particularly,a hybrid network architecture that includes surface buoys,anchor nodes,active sensor nodes and ordinary sensor nodes is constructed.Then,an asynchronous localization protocol is provided,through which two privacy-preserving localization algorithms are designed to estimate the locations of active and ordinary sensor nodes.It is worth mentioning that,the proposed localization algorithms reveal disguised positions to the network,while they do not adopt any homomorphic encryption technique.More importantly,they can eliminate the effect of asynchronous clock,i.e.,clock skew and offset.The performance analyses for the privacy-preserving asynchronous localization algorithms are also presented.Finally,simulation and experiment results reveal that the proposed localization approach can avoid the leakage of position information,while the location accuracy can be significantly enhanced as compared with the other works.

ε-inclusion: privacy preserving re-publication of dynamic datasets

This paper presents a novel privacy principle, ε-inclusion, for re-publishing sensitive dynamic datasets. ε-inclusion releases all the quasi-identifier values directly and uses permutation-based method and substitution to anonymize the microdata. Combined with generalization-based methods, ε-inclusion protects privacy and captures a large amount of correlation in the microdata. We develop an effective algorithm for computing anonymized tables that obey the ε-inclusion privacy requirement. Extensive experiments confirm that our solution allows significantly more effective data analysis than generalization-based methods.

A Cloud-Fog Enabled and Privacy-Preserving IoT Data Market Platform Based on Blockchain

The dynamic landscape of the Internet of Things(IoT)is set to revolutionize the pace of interaction among entities,ushering in a proliferation of applications characterized by heightened quality and diversity.Among the pivotal applications within the realm of IoT,as a significant example,the Smart Grid(SG)evolves into intricate networks of energy deployment marked by data integration.This evolution concurrently entails data interchange with other IoT entities.However,there are also several challenges including data-sharing overheads and the intricate establishment of trusted centers in the IoT ecosystem.In this paper,we introduce a hierarchical secure data-sharing platform empowered by cloud-fog integration.Furthermore,we propose a novel non-interactive zero-knowledge proof-based group authentication and key agreement protocol that supports one-to-many sharing sets of IoT data,especially SG data.The security formal verification tool shows that the proposed scheme can achieve mutual authentication and secure data sharing while protecting the privacy of data providers.Compared with previous IoT data sharing schemes,the proposed scheme has advantages in both computational and transmission efficiency,and has more superiority with the increasing volume of shared data or increasing number of participants.

Privacy-Preserving Healthcare and Medical Data Collaboration Service System Based on Blockchain and Federated Learning

As the volume of healthcare and medical data increases from diverse sources,real-world scenarios involving data sharing and collaboration have certain challenges,including the risk of privacy leakage,difficulty in data fusion,low reliability of data storage,low effectiveness of data sharing,etc.To guarantee the service quality of data collaboration,this paper presents a privacy-preserving Healthcare and Medical Data Collaboration Service System combining Blockchain with Federated Learning,termed FL-HMChain.This system is composed of three layers:Data extraction and storage,data management,and data application.Focusing on healthcare and medical data,a healthcare and medical blockchain is constructed to realize data storage,transfer,processing,and access with security,real-time,reliability,and integrity.An improved master node selection consensus mechanism is presented to detect and prevent dishonest behavior,ensuring the overall reliability and trustworthiness of the collaborative model training process.Furthermore,healthcare and medical data collaboration services in real-world scenarios have been discussed and developed.To further validate the performance of FL-HMChain,a Convolutional Neural Network-based Federated Learning(FL-CNN-HMChain)model is investigated for medical image identification.This model achieves better performance compared to the baseline Convolutional Neural Network(CNN),having an average improvement of 4.7%on Area Under Curve(AUC)and 7%on Accuracy(ACC),respectively.Furthermore,the probability of privacy leakage can be effectively reduced by the blockchain-based parameter transfer mechanism in federated learning between local and global models.

Reliable Medical Recommendation Based on Privacy-Preserving Collaborative Filtering

Collaborative filtering(CF)methods are widely adopted by existing medical recommendation systems,which can help clinicians perform their work by seeking and recommending appropriate medical advice.However,privacy issue arises in this process as sensitive patient private data are collected by the recommendation server.Recently proposed privacy-preserving collaborative filtering methods,using computation-intensive cryptography techniques or data perturbation techniques are not appropriate in medical online service.The aim of this study is to address the privacy issues in the context of neighborhoodbased CF methods by proposing a Privacy Preserving Medical Recommendation(PPMR)algorithm,which can protect patients’treatment information and demographic information during online recommendation process without compromising recommendation accuracy and efficiency.The proposed algorithm includes two privacy preserving operations:Private Neighbor Selection and Neighborhood-based Differential Privacy Recommendation.Private Neighbor Selection is conducted on the basis of the notion of k-anonymity method,meaning that neighbors are privately selected for the target user according to his/her similarities with others.Neighborhood-based Differential Privacy Recommendation and a differential privacy mechanism are introduced in this operation to enhance the performance of recommendation.Our algorithm is evaluated using the real-world hospital EMRs dataset.Experimental results demonstrate that the proposed method achieves stable recommendation accuracy while providing comprehensive privacy for individual patients.

Privacy-Preserving Prepayment Based Power Request and Trading in Smart Grid

Demand response has been intensively studied in recent years. It can motivate customers to change their consumption patterns according to the dynamic(time-varying) electricity price, which is considered to be the most cost-effective and reliable solution for smoothing the demand curve. However, many existing schemes, based on users' demand request in each period, require users to consume their requested electricity exactly, which sometimes causes inconvenience and losses to the utility, because customers cannot always be able to consume the accurate electricity demand due to various personal reasons. In this paper, we tackle this problem in a novel approach. Instead of charging after consumption, we adopt the prepayment mechanism to implement power request. Furthermore, we propose a trading market running by the control center to cope with the users' dynamic demand. It is noteworthy that both users' original demand and trading records are protected against potential adversaries including the curious control center. Through the numerical simulation, we demonstrate that our scheme is highly efficient in both computation and communication.

FedCDR:Privacy-preserving federated cross-domain recommendation

Cross-Domain Recommendation(CDR)aims to solve data sparsity and cold-start problems by utilizing a relatively information-rich source domain to improve the recommendation performance of the data-sparse target domain.However,most existing approaches rely on the assumption of centralized storage of user data,which undoubtedly poses a significant risk of user privacy leakage because user data are highly privacy-sensitive.To this end,we propose a privacy-preserving Federated framework for Cross-Domain Recommendation,called FedCDR.In our method,to avoid leakage of user privacy,a general recommendation model is trained on each user's personal device to obtain embeddings of users and items,and each client uploads weights to the central server.The central server then aggregates the weights and distributes them to each client for updating.Furthermore,because the weights implicitly contain private information about the user,local differential privacy is adopted for the gradients before uploading them to the server for better protection of user privacy.To distill the relationship of user embedding between two domains,an embedding transformation mechanism is used on the server side to learn the cross-domain embedding transformation model.Extensive experiments on real-world datasets demonstrate that ourmethod achieves performance comparable with that of existing data-centralized methods and effectively protects user privacy.

NLDA non-linear regression model for preserving data privacy in wireless sensor networks

Recently,the application of Wireless Sensor Networks(WSNs)has been increasing rapidly.It requires privacy preserving data aggregation protocols to secure the data from compromises.Preserving privacy of the sensor data is a challenging task.This paper presents a non-linear regression-based data aggregation protocol for preserving privacy of the sensor data.The proposed protocol uses non-linear regression functions to represent the sensor data collected from the sensor nodes.Instead of sending the complete data to the cluster head,the sensor nodes only send the coefficients of the non-linear function.This will reduce the communication overhead of the network.The data aggregation is performed on the masked coefficients and the sink node is able to retrieve the approximated results over the aggregated data.The analysis of experiment results shows that the proposed protocol is able to minimize communication overhead,enhance data aggregation accuracy,and preserve data privacy.

Pri-EMO:A universal perturbation method for privacy preserving facial emotion recognition

Facial emotion have great significance in human-computer interaction,virtual reality and people's communication.Existing methods for facial emotion privacy mainly concentrate on the perturbation of facial emotion images.However,cryptography-based perturbation algorithms are highly computationally expensive,and transformation-based perturbation algorithms only target specific recognition models.In this paper,we propose a universal feature vector-based privacy-preserving perturbation algorithm for facial emotion.Our method implements privacy-preserving facial emotion images on the feature space by computing tiny perturbations and adding them to the original images.In addition,the proposed algorithm can also enable expression images to be recognized as specific labels.Experiments show that the protection success rate of our method is above 95%and the image quality evaluation degrades no more than 0.003.The quantitative and qualitative results show that our proposed method has a balance between privacy and usability.

Lightweight privacy-preserving truth discovery for vehicular air quality monitoring

Air pollution has become a global concern for many years.Vehicular crowdsensing systems make it possible to monitor air quality at a fine granularity.To better utilize the sensory data with varying credibility,truth discovery frameworks are introduced.However,in urban cities,there is a significant difference in traffic volumes of streets or blocks,which leads to a data sparsity problem for truth discovery.Protecting the privacy of participant vehicles is also a crucial task.We first present a data masking-based privacy-preserving truth discovery framework,which incorporates spatial and temporal correlations to solve the sparsity problem.To further improve the truth discovery performance of the presented framework,an enhanced version is proposed with anonymous communication and data perturbation.Both frameworks are more lightweight than the existing cryptography-based methods.We also evaluate the work with simulations and fully discuss the performance and possible extensions.

BPPF:Bilateral Privacy-Preserving Framework for Mobile Crowdsensing

With the emergence of mobile crowdsensing (MCS), merchants can use their mobiledevices to collect data that customers are interested in. Now there are many mobilecrowdsensing platforms in the market, such as Gigwalk, Uber and Checkpoint, which publishand select the right workers to complete the task of some specific locations (for example,taking photos to collect the price of goods in a shopping mall). In mobile crowdsensing, in orderto select the right workers, the platform needs the actual location information of workersand tasks, which poses a risk to the location privacy of workers and tasks. In this paper, westudy privacy protection in MCS. The main challenge is to assign the most suitable worker toa task without knowing the task and the actual location of the worker. We propose a bilateralprivacy protection framework based on matrix multiplication, which can protect the locationprivacy between the task and the worker, and keep their relative distance unchanged.