Biblio

In this paper, we propose a scheme that supports statistic query and authorized access control on an Encrypted Electronic Medical Records Databases(EMDB). Different from other schemes, it is based on Differential-Privacy(DP), which can protect the privacy of patients. By deploying an improved Multi-Authority Attribute-Based Encryption(MA-ABE) scheme, all authorities can distribute their search capability to clients under different authorities without additional negotiations. To our best knowledge, there are few studies on statistical queries on encrypted data. In this work, we consider that support differentially-private statistical queries. To improve search efficiency, we leverage the Bloom Filter(BF) to judge whether the keywords queried by users exists. Finally, we use experiments to verify and evaluate the feasibility of our proposed scheme.

With the development of 5G technology and intelligent terminals, the future direction of the Industrial Internet of Things (IIoT) evolution is Pervasive Edge Computing (PEC). In the pervasive edge computing environment, intelligent terminals can perform calculations and data processing. By migrating part of the original cloud computing model's calculations to intelligent terminals, the intelligent terminal can complete model training without uploading local data to a remote server. Pervasive edge computing solves the problem of data islands and is also successfully applied in scenarios such as vehicle interconnection and video surveillance. However, pervasive edge computing is facing great security problems. Suppose the remote server is honest but curious. In that case, it can still design algorithms for the intelligent terminal to execute and infer sensitive content such as their identity data and private pictures through the information returned by the intelligent terminal. In this paper, we research the problem of honest but curious remote servers infringing intelligent terminal privacy and propose a differential privacy collaborative deep learning algorithm in the pervasive edge computing environment. We use a Gaussian mechanism that meets the differential privacy guarantee to add noise on the first layer of the neural network to protect the data of the intelligent terminal and use analytical moments accountant technology to track the cumulative privacy loss. Experiments show that with the Gaussian mechanism, the training data of intelligent terminals can be protected reduction inaccuracy.

Recommender systems have been proved to be effective techniques to provide users with better experiences. However, when a recommender knows the user's preference characteristics or gets their sensitive information, then a series of privacy concerns are raised. A amount of solutions in the literature have been proposed to enhance privacy protection degree of recommender systems. Although the existing solutions have enhanced the protection, they led to a decrease in recommendation accuracy simultaneously. In this paper, we propose a security-aware hybrid recommendation method by combining the factorization and regression techniques. Specifically, the differential privacy mechanism is integrated into data pre-processing for data encryption. Firstly data are perturbed to satisfy differential privacy and transported to the recommender. Then the recommender calculates the aggregated data. However, applying differential privacy raises utility issues of low recommendation accuracy, meanwhile the use of a single model may cause overfitting. In order to tackle this challenge, we adopt a fusion prediction model by combining linear regression (LR) and matrix factorization (MF) for collaborative recommendation. With the MovieLens dataset, we evaluate the recommendation accuracy and regression of our recommender system and demonstrate that our system performs better than the existing recommender system under privacy requirement.

Big data continues to grow in the manufacturing domain due to increasing interconnectivity on the shop floor in the course of the fourth industrial revolution. The optimization of machines based on either real-time or historical machine data provides benefits to both machine producers and operators. In order to be able to make use of these opportunities, it is necessary to access the machine data, which can include sensitive information such as intellectual property. Employing the use case of machine tools, this paper presents a solution enabling industrial data sharing and cloud collaboration while protecting sensitive information. It employs the edge computing paradigm to apply differential privacy to machine data in order to protect sensitive information and simultaneously allow machine producers to perform the necessary calculations and analyses using this data.

In recent times, the use of cloud computing has gained popularity all over the world in the context of performing smart computations on big data. The privacy of sensitive data of the client is of utmost important issues. Data leakage or hijackers may theft significant information about the client that ultimately may affect the reputation and prestige of its owner (bank) and client (customers). In general, to save the privacy of our banking data it is preferred to store, process, and transmit the data in the form of encrypted text. But now the main concern leads to secure computation over encrypted text or another possible way to perform computation over clouds makes data more vulnerable to hacking and attacks. Existing classical encryption techniques such as RSA, AES, and others provide secure transaction procedures for data over clouds but these are not fit for secure computation over data in the clouds. In 2009, Gentry comes with a solution for such issues and presents his idea as Homomorphic encryption (HE) that can perform computation over encrypted text without decrypting the data itself. Now a day's privacy-enhancing techniques (PET) are there to explore more potential benefits in security issues and useful in historical cases of privacy failure. Differential privacy, Federated analysis, homomorphic encryption, zero-knowledge proof, and secure multiparty computation are a privacy-enhancing technique that may useful in financial services as these techniques provide a fully-fledged mechanism for financial institutes. With the collaboration of industries, these techniques are may enable new data-sharing agreements for a more secure solution over data. In this paper, the primary concern is to investigate the different standards and properties of homomorphic encryption in digital banking and financial institutions.

Recently, federated learning (FL), as an advanced and practical solution, has been applied to deal with privacy-preserving issues in distributed multi-party federated modeling. However, most existing FL methods focus on the same privacy-preserving budget while ignoring various privacy requirements of participants. In this paper, we for the first time propose an algorithm (PLU-FedOA) to optimize the deep neural network of horizontal FL with personalized local differential privacy. For such considerations, we design two approaches: PLU, which allows clients to upload local updates under differential privacy-preserving of personally selected privacy level, and FedOA, which helps the server aggregates local parameters with optimized weight in mixed privacy-preserving scenarios. Moreover, we theoretically analyze the effect on privacy and optimization of our approaches. Finally, we verify PLU-FedOA on real-world datasets.

Keystroke dynamics is a behavioural biometric form of authentication based on the inherent typing behaviour of an individual. While this technique is gaining traction, protecting the privacy of the users is of utmost importance. Fully Homomorphic Encryption is a technique that allows performing computation on encrypted data, which enables processing of sensitive data in an untrusted environment. FHE is also known to be “future-proof” since it is a lattice-based cryptosystem that is regarded as quantum-safe. It has seen significant performance improvements over the years with substantially increased developer-friendly tools. We propose a neural network for keystroke analysis trained using differential privacy to speed up training while preserving privacy and predicting on encrypted data using FHE to keep the users' privacy intact while offering sufficient usability.

Federated learning (FL) allows to train a massive amount of data privately due to its decentralized structure. Stochastic gradient descent (SGD) is commonly used for FL due to its good empirical performance, but sensitive user information can still be inferred from weight updates shared during FL iterations. We consider Gaussian mechanisms to preserve local differential privacy (LDP) of user data in the FL model with SGD. The trade-offs between user privacy, global utility, and transmission rate are proved by defining appropriate metrics for FL with LDP. Compared to existing results, the query sensitivity used in LDP is defined as a variable, and a tighter privacy accounting method is applied. The proposed utility bound allows heterogeneous parameters over all users. Our bounds characterize how much utility decreases and transmission rate increases if a stronger privacy regime is targeted. Furthermore, given a target privacy level, our results guarantee a significantly larger utility and a smaller transmission rate as compared to existing privacy accounting methods.

With the development of network, network security has become a topic of increasing concern. Recent years, machine learning technology has become an effective means of network intrusion detection. However, machine learning technology requires a large amount of data for training, and training data often contains privacy information, which brings a great risk of privacy leakage. At present, there are few researches on data privacy protection in the field of intrusion detection. Regarding the issue of privacy and security, we combine differential privacy and machine learning algorithms, including One-class Support Vector Machine (OCSVM) and Local Outlier Factor(LOF), to propose an hybrid intrusion detection system (IDS) with privacy protection. We add Laplacian noise to the original network intrusion detection data set to get differential privacy data sets with different privacy budgets, and proposed a hybrid IDS model based on machine learning to verify their utility. Experiments show that while protecting data privacy, the hybrid IDS can achieve detection accuracy comparable to traditional machine learning algorithms.

Pedestrian dead reckoning (PDR) is a widely used approach to estimate locations and trajectories. Accessing location-based services with trajectory data can bring convenience to people, but may also raise privacy concerns that need to be addressed. In this paper, a privacy-preserving pedestrian dead reckoning framework is proposed to protect a user’s trajectory privacy based on differential privacy. We introduce two metrics to quantify trajectory privacy and data utility. Our proposed privacy-preserving trajectory extraction algorithm consists of three mechanisms for the initial locations, stride lengths and directions. In addition, we design an adversary model based on particle filtering to evaluate the performance and demonstrate the effectiveness of our proposed framework with our collected sensor reading dataset.

Differential privacy is a concept to quantity the disclosure of private information that is controlled by the privacy parameter ε. However, an intuitive interpretation of ε is needed to explain the privacy loss to data engineers and data subjects. In this paper, we conduct a worst-case study of differential privacy risks. We generalize an existing model and reduce complexity to provide more understandable statements on the privacy loss. To this end, we analyze the impact of parameters and introduce the notion of a global privacy risk and global privacy leak.

Current implementations of Differential Privacy (DP) focus primarily on the privacy of the data release. The planned thesis will investigate steps towards a user-centric approach of DP in the scope of the Internet-of-Things (IoT) which focuses on data subjects, IoT developers, and data analysts. We will conduct user studies to find out more about the often conflicting interests of the involved parties and the encountered challenges. Furthermore, a technical solution will be developed to assist data subjects and analysts in making better informed decisions. As a result, we expect our contributions to be a step towards the development of usable DP for IoT sensor data.

With the rapid development of 5G, the Internet of Things (IoT) and edge computing technologies dramatically improve smart industries' efficiency, such as healthcare, smart agriculture, and smart city. IoT is a data-driven system in which many smart devices generate and collect a massive amount of user privacy data, which may be used to improve users' efficiency. However, these data tend to leak personal privacy when people send it to the Internet. Differential privacy (DP) provides a method for measuring privacy protection and a more flexible privacy protection algorithm. In this paper, we study an estimation problem and propose a new frequency estimation algorithm named MFEA that redesigns the publish process. The algorithm maps a finite data set to an integer range through a hash function, then initializes the data vector according to the mapped value and adds noise through the randomized response. The frequency of all interference data is estimated with maximum likelihood. Compared with the current traditional frequency estimation, our approach achieves better algorithm complexity and error control while satisfying differential privacy protection (LDP).

Smart meter devices enable a better understanding of the demand at the potential risk of private information leakage. One promising solution to mitigating such risk is to inject noises into the meter data to achieve a certain level of differential privacy. In this paper, we cast one-shot non-intrusive load monitoring (NILM) in the compressive sensing framework, and bridge the gap between theoretical accuracy of NILM inference and differential privacy's parameters. We then derive the valid theoretical bounds to offer insights on how the differential privacy parameters affect the NILM performance. Moreover, we generalize our conclusions by proposing the hierarchical framework to solve the multishot NILM problem. Numerical experiments verify our analytical results and offer better physical insights of differential privacy in various practical scenarios. This also demonstrates the significance of our work for the general privacy preserving mechanism design.

Noise has been used as a way of protecting privacy of users in public datasets for many decades now. Differential privacy is a new standard to add noise, so that user privacy is protected. When this technique is applied for a single end user data, it's called local differential privacy. In this study, we evaluate the effects of adding noise to generate randomized responses on machine learning models. We generate randomized responses using Gaussian, Laplacian noise on singular end user data as well as correlated end user data. Finally, we provide results that we have observed on a few data sets for various machine learning use cases.

Cyber-physical systems (CPS) data privacy protection during sharing, aggregating, and publishing is a challenging problem. Several privacy protection mechanisms have been developed in the literature to protect sensitive data from adversarial analysis and eliminate the risk of re-identifying the original properties of shared data. However, most of the existing solutions have drawbacks, such as (i) lack of a proper vulnerability characterization model to accurately identify where privacy is needed, (ii) ignoring data providers privacy preference, (iii) using uniform privacy protection which may create inadequate privacy for some provider while over-protecting others, and (iv) lack of a comprehensive privacy quantification model assuring data privacy-preservation. To address these issues, we propose a personalized privacy preference framework by characterizing and quantifying the CPS vulnerabilities as well as ensuring privacy. First, we introduce a Standard Vulnerability Profiling Library (SVPL) by arranging the nodes of an energy-CPS from maximum to minimum vulnerable based on their privacy loss. Based on this model, we present our personalized privacy framework (PDP) in which Laplace noise is added based on the individual node's selected privacy preferences. Finally, combining these two proposed methods, we demonstrate that our privacy characterization and quantification model can attain better privacy preservation by eliminating the trade-off between privacy, utility, and risk of losing information.

The integration of advanced information, communication and data analytic technologies has transformed the traditional grid into an intelligent bidirectional system that can automatically adapt its services for utilities or consumers' needs. However, this change raises new privacy-related challenges. Privacy leakage has become a severe issue in the grid paradigm as adversaries run malicious analytics to identify the system's internal insight or use it to interrupt grids' operation by identifying real-time demand-based supply patterns. As a result, current grid authorities require an integrated mechanism to improve the system's sensitive data's privacy preservation. To this end, we present a multilayered smart grid architecture by characterizing the privacy issues that occur during data sharing, aggregation, and publishing by individual grid end nodes. Based on it, we quantify the nodes preferred privacy requirements. We further introduce personalized differential privacy (PDP) scheme based on trust distance in our proposed framework to provide the system with the added benefit of a user-specific privacy guarantee to eliminate differential privacy's limitation that allows the same level of privacy for all data providers. Lastly, we conduct extensive experimental analysis on a real-world grid dataset to illustrate that our proposed method is efficient enough to provide privacy preservation on sensitive smart grid data.

Strings are used to model genomic, natural language, and web activity data, and are thus often shared broadly. However, string data sharing has raised privacy concerns stemming from the fact that knowledge of length-k substrings of a string and their frequencies (multiplicities) may be sufficient to uniquely reconstruct the string; and from that the inference of such substrings may leak confidential information. We thus introduce the problem of protecting length-k substrings of a single string S by applying Differential Privacy (DP) while maximizing data utility for frequency-based mining tasks. Our theoretical and empirical evidence suggests that classic DP mechanisms are not suitable to address the problem. In response, we employ the order-k de Bruijn graph G of S and propose a sampling-based mechanism for enforcing DP on G. We consider the task of enforcing DP on G using our mechanism while preserving the normalized edge multiplicities in G. We define an optimization problem on integer edge weights that is central to this task and develop an algorithm based on dynamic programming to solve it exactly. We also consider two variants of this problem with real edge weights. By relaxing the constraint of integer edge weights, we are able to develop linear-time exact algorithms for these variants, which we use as stepping stones towards effective heuristics. An extensive experimental evaluation using real-world large-scale strings (in the order of billions of letters) shows that our heuristics are efficient and produce near-optimal solutions which preserve data utility for frequency-based mining tasks.

In federated learning, machine learning and deep learning models are trained globally on distributed devices. The state-of-the-art privacy-preserving technique in the context of federated learning is user-level differential privacy. However, such a mechanism is vulnerable to some specific model poisoning attacks such as Sybil attacks. A malicious adversary could create multiple fake clients or collude compromised devices in Sybil attacks to mount direct model updates manipulation. Recent works on novel defense against model poisoning attacks are difficult to detect Sybil attacks when differential privacy is utilized, as it masks clients' model updates with perturbation. In this work, we implement the first Sybil attacks on differential privacy based federated learning architectures and show their impacts on model convergence. We randomly compromise some clients by manipulating different noise levels reflected by the local privacy budget ε of differential privacy with Laplace mechanism on the local model updates of these Sybil clients. As a result, the global model convergence rates decrease or even leads to divergence. We apply our attacks to two recent aggregation defense mechanisms, called Krum and Trimmed Mean. Our evaluation results on the MNIST and CIFAR-10 datasets show that our attacks effectively slow down the convergence of the global models. We then propose a method to keep monitoring the average loss of all participants in each round for convergence anomaly detection and defend our Sybil attacks based on the training loss reported from randomly selected sets of clients as the judging panels. Our empirical study demonstrates that our defense effectively mitigates the impact of our Sybil attacks.

Federated learning is a privacy-preserving learning system where participants locally update a shared model with their own training data. Despite the advantage that training data are not sent to a server, there is still a risk that a state-of-the-art model inversion attack, which may be conducted by the server, infers training data from the models updated by the participants, referred to as individual models. A solution to prevent such attacks is differential privacy, where each participant adds noise to the individual model before sending it to the server. Differential privacy, however, sacrifices the quality of the shared model in compensation for the fact that participants' training data are not leaked. This paper proposes a federated learning system that is resistant to model inversion attacks without sacrificing the quality of the shared model. The core idea is that each participant divides the individual model into model fragments, shuffles, and aggregates them to prevent adversaries from inferring training data. The other benefit of the proposed system is that the resulting shared model is identical to the shared model generated with the naive federated learning.

Differentially private (DP) machine learning allows us to train models on private data while limiting data leakage. DP formalizes this data leakage through a cryptographic game, where an adversary must predict if a model was trained on a dataset D, or a dataset D′ that differs in just one example. If observing the training algorithm does not meaningfully increase the adversary's odds of successfully guessing which dataset the model was trained on, then the algorithm is said to be differentially private. Hence, the purpose of privacy analysis is to upper bound the probability that any adversary could successfully guess which dataset the model was trained on.In our paper, we instantiate this hypothetical adversary in order to establish lower bounds on the probability that this distinguishing game can be won. We use this adversary to evaluate the importance of the adversary capabilities allowed in the privacy analysis of DP training algorithms.For DP-SGD, the most common method for training neural networks with differential privacy, our lower bounds are tight and match the theoretical upper bound. This implies that in order to prove better upper bounds, it will be necessary to make use of additional assumptions. Fortunately, we find that our attacks are significantly weaker when additional (realistic) restrictions are put in place on the adversary's capabilities. Thus, in the practical setting common to many real-world deployments, there is a gap between our lower bounds and the upper bounds provided by the analysis: differential privacy is conservative and adversaries may not be able to leak as much information as suggested by the theoretical bound.

Smart grid achieves reliable, efficient and flexible grid data processing by integrating traditional power grid with information and communication technology. The control center can evaluate the supply and demand of the power grid through aggregated data of users, and then dynamically adjust the power supply, price of the power, etc. However, since the grid data collected from users may disclose the user's electricity using habits and daily activities, the privacy concern has become a critical issue. Most of the existing privacy-preserving data collection schemes for smart grid adopt homomorphic encryption or randomization techniques which are either impractical because of the high computation overhead or unrealistic for requiring the trusted third party. In this paper, we propose a privacy-preserving smart grid data aggregation scheme satisfying local differential privacy (LDP) based on randomized response. Our scheme can achieve efficient and practical estimation of the statistics of power supply and demand while preserving any individual participant's privacy. The performance analysis shows that our scheme is efficient in terms of computation and communication overhead.

Smart Meters (SM) are IoT end devices used to collect user utility consumption with limited processing power on the edge of the smart grid (SG). While SMs have great applications in providing data analysis to the utility provider and consumers, private user information can be inferred from SMs readings. For preserving user privacy, a number of methods were developed that use perturbation by adding noise to alter user load and hide consumer data. Most methods limit the amount of perturbation noise using differential privacy to preserve the benefits of data analysis. However, additive noise perturbation may have an undesirable effect on billing. Additionally, users may desire to select complete privacy without giving consent to having their data analyzed. We present a virtual battery model that uses perturbation with additive noise obtained from a virtual chargeable battery. The level of noise can be set to make user data differentially private preserving statistics or break differential privacy discarding the benefits of data analysis for more privacy. Our model uses fog aggregation with authentication and encryption that employs lightweight cryptographic primitives. We use Diffie-Hellman key exchange for symmetrical encryption of transferred data and a two-way challenge-response method for authentication.

The recommender system is an important application in big data analytics because accurate recommendation items or high-valued suggestions can bring high profit to both commercial companies and customers. To make precise recommendations, a recommender system often needs large and fine-grained data for training. In the current big data era, data often exist in the form of isolated islands, and it is difficult to integrate the data scattered due to privacy security concerns. Moreover, privacy laws and regulations make it harder to share data. Therefore, designing a privacy-preserving recommender system is of paramount importance. Existing privacy-preserving recommender system models mainly adapt cryptography approaches to achieve privacy preservation. However, cryptography approaches have heavy overhead when performing encryption and decryption operations and they lack a good level of flexibility. In this paper, we propose a Locality Sensitive Hashing (LSH) based approach for federated recommender system. Our proposed efficient and scalable federated recommender system can make full use of multiple source data from different data owners while guaranteeing preservation of privacy of contributing parties. Extensive experiments on real-world benchmark datasets show that our approach can achieve both high time efficiency and accuracy under small privacy budgets.

Balancing utility and differential privacy by shuffling or BUDS is an approach towards crowd sourced, statistical databases, with strong privacy and utility balance using differential privacy theory. Here, a novel algorithm is proposed using one-hot encoding and iterative shuffling with the loss estimation and risk minimization techniques, to balance both the utility and privacy. In this work, after collecting one-hot encoded data from different sources and clients, a step of novel attribute shuffling technique using iterative shuffling (based on the query asked by the analyst) and loss estimation with an updation function and risk minimization produces a utility and privacy balanced differential private report. During empirical test of balanced utility and privacy, BUDS produces ε = 0.02 which is a very promising result. Our algorithm maintains a privacy bound of ε = ln[t/((n1-1)S)] and loss bound of c'\textbackslashtextbareln[t/((n1-1)S)]-1\textbackslashtextbar.