Reconfigurable Intelligent Surface (RIS) has emerged as a pivotal technology in the development of sixth-generation (6G) mobile communication systems. In this paper, a wireless communication system assisted by RIS in the air is studied, in which RIS is installed on the UAV as a mobile relay (RIS-UAV) to re-establish the line-of-sight (LoS) link between the base station and users. Considering the active beamforming vector of base station, UAV trajectory and phase shift of RIS, a joint optimization scheme is proposed to maximize the energy efficiency of the system. Aiming at this optimization problem, a dual DDQN structure algorithm (PER-TDDQN) based on priority experience replay mechanism is proposed to solve this multi-objective joint optimization problem. The simulation results show that the proposed algorithm can effectively improve the energy efficiency of the system.

The rapid development of indoor location-based services (LBS) has raised concerns about location privacy protection in the 3-dimensional (3D) space. The existing 2-dimensional (2D) location privacy protection mechanisms (LPPMs) cannot effectively resist attacks in 3D environments. Furthermore, users may have various sensitive attributes at different locations and times. In this paper, we first formally study the relationship between two complementary notions of geo-indistinguishability and distortion privacy (i.e., expected inference error) in the 3D space and develop a two-phase personalized 3D LPPM (P3DLPPM). In Phase I, we search for neighboring locations to formulate a protection location set (PLS) for hiding the actual location based on the above-mentioned relationship. To realize this, we develop a 3D Hilbert curve-based minimum distance searching algorithm to find the PLS with minimum diameter for each location while guaranteeing differential privacy. In Phase II, we put forth a novel Permute-and-Flip mechanism for location perturbation, which maps its initial application in data publishing privacy protection to a location perturbation mechanism. It generates fake locations with smaller perturbation distances while improving the balance between privacy and quality of service (QoS). Simulation results show that the proposed P3DLPPM can significantly improve personalized privacy protection while meeting the user's QoS needs.

(Gradient) Expectation Maximization (EM) is a widely used algorithm for estimating the maximum likelihood of mixture models or incomplete data problems. A major challenge facing this popular technique is how to effectively preserve the privacy of sensitive data. Previous research on this problem has already lead to the discovery of some Differentially Private (DP) algorithms for (Gradient) EM. However, unlike in the non-private case, existing techniques are not yet able to provide finite sample statistical guarantees. To address this issue, we propose in this paper the first DP version of Gradient EM algorithm with statistical guarantees. Specifically, we first propose a new mechanism for privately estimating the mean of a heavy-tailed distribution, which significantly improves a previous result in [25], and it could be extended to the local DP model, which has not been studied before. Next, we apply our general framework to three canonical models: Gaussian Mixture Model (GMM), Mixture of Regressions Model (MRM) and Linear Regression with Missing Covariates (RMC). Specifically, for GMM in the DP model, our estimation error is near optimal in some cases. For the other two models, we provide the first result on finite sample statistical guarantees. Our theory is supported by thorough numerical experiments on both real-world data and synthetic data.

Recent rapid development of sensor technology has allowed massive time series data to be collected and set foundation for the development of data-driven services and applications. During the process, data sharing is often required to allow modelers to perform specific time series data mining tasks based on the need of data owner. The high resolution of time series data brings new challenges in privacy protection, as meaningful information in high-resolution data shifts from concrete point values to shape-based patterns. Numerous research efforts have found that long shape-based patterns could contain more sensitive information and may potentially be extracted and misused by a malicious modeler. However, the privacy issue for time series patterns is surprisingly seldom explored in privacy-preserving literature. In this work, we consider a new privacy preserving problem: preventing malicious inference on long shape-based patterns while preserving short segment information to maintain utility task performance. To mitigate the challenge, we investigate an alternative approach by sharing Matrix Profile (MP), a versatile data structure that supports many time series data mining tasks. We found that while MP can prevent the concrete shape leakage, the canonical correlation in MP index can still reveal the location of sensitive long pattern information. Based on this observation, we design two attacks named Location Attack and Entropy Attack to extract the pattern location from MP. To further protect MP from these two attacks, we propose a Privacy-Aware Matrix Profile (PMP) via perturbing the local correlation and breaking the canonical correlation in MP index vector. We evaluate our proposed PMP against baseline noise-adding methods through quantitative analysis and real-world case study to show the effectiveness of the proposed method. Our source code is available at https://github.com/lzhang18/PMP.

Federated learning (FL) through its novel applications and services has enhanced its presence as a promising tool in the Internet of Things (IoT) domain. Specifically, in a multiaccess edge computing setup with a host of IoT devices, FL is most suitable since it leverages distributed client data to train high-performance deep learning (DL) models while keeping the data private. However, the underlying deep neural networks (DNNs) are huge, preventing its direct deployment onto resource-constrained computing and memory-limited IoT devices. Besides, frequent exchange of model updates between the central server and clients in FL could result in a communication bottleneck. To address these challenges, in this article, we introduce GWEP, a model compression-based FL method. It utilizes joint quantization and model pruning to reap the benefits of DNNs while meeting the capabilities of resource-constrained devices. Consequently, by reducing the computational, memory, and network footprint of FL, the low-end IoT devices may be able to participate in the FL process. In addition, we provide theoretical guarantees of FL convergence. Through empirical evaluations, we demonstrate that our approach significantly outperforms the baseline algorithms by being up to 10.23 times faster with 11 times lesser communication rounds, while achieving high-model compression, energy efficiency, and learning performance.

With the wide range application of machine learning in healthcare for helping humans drive crucial decisions, data privacy becomes an inevitable concern due to the utilization of sensitive data such as patients records and registers of a company. Thus, constructing a privacy preserving machine learning model while still maintaining high accuracy becomes a challenging problem. In this article, we propose two differentially private algorithms, i.e., Output Perturbation with aGM (OPERA) and Gradient Perturbation with aGM (GRPUA) for empirical risk minimization, a useful method to obtain a globally optimal classifier, by leveraging the analytic Gaussian mechanism (aGM) to achieve privacy preservation of sensitive medical data in a healthcare system. We theoretically analyze and prove utility upper bounds of proposed algorithms and compare them with prior algorithms in the literature. The analyses show that in the high privacy regime, our proposed algorithms can achieve a tighter utility bound for both settings: strongly convex and non-strongly convex loss functions. Besides, we evaluate the proposed private algorithms on five benchmark datasets. The simulation results demonstrate that our approaches can achieve higher accuracy and lower objective values compared with existing ones in all three datasets while providing differential privacy guarantees.

Indoor location-based services (LBS) are widely used in large-scale indoor buildings, such as high-rise hospitals and multi-story shopping malls. At the same time, location privacy protection in such three-dimensional (3D) space has recently attracted considerable attention. Currently, most existing location privacy protection schemes focus on two-dimensional (2D) location protection and fail to prevent location inference attacks when the user’s location data include height dimension, i.e., 3D geolocation. Enlightened by the concept of differential privacy, in this paper we first study the impact factors of the degree of indistinguishability of 3D geolocations. Then, we quantify location privacy for LBS applications in the 3D space with geo-indistinguishability (3D-GI) rigorously and provably. We develop a mechanism of three-variates Laplacian to generate perturbed locations considering the locations’ X, Y, and Z-coordinates simultaneously, guaranteeing geo-indistinguishability. Furthermore, the discretization noise-adding mechanism is studied to satisfy geo-indistinguishability in the 3D space under the finite precision of hardware/devices. Considering the discretized mechanism can only satisfy geo-indistinguishability in finite 3D space and users visit the limited regions, we further study the truncation of the Laplacian mechanism to limit the generated perturbed locations within a specific region. Simulation results demonstrate that the proposed 3D-GI outperforms the benchmarks while guaranteeing privacy regardless of the adversary’s prior knowledge.

Collaborative learning has received huge interests due to its capability of exploiting the collective computing power of the wireless edge devices. However, during the learning process, model updates using local private samples and large-scale parameter exchanges among agents impose severe privacy concerns and communication bottleneck. In this paper, to address these problems, we propose two differentially private (DP) and communication efficient algorithms, called Q-DPSGD-1 and Q-DPSGD-2. In Q-DPSGD-1, each agent first performs local model updates by a DP gradient descent method to provide the DP guarantee and then quantizes the local model before transmitting it to neighbors to improve communication efficiency. In Q-DPSGD-2, each agent injects discrete Gaussian noise to enforce DP guarantee after first quantizing the local model. Moreover, we track the privacy loss of both approaches under the Renyi DP and provide convergence analysis for both convex and non-convex loss functions. The proposed methods are evaluated in extensive experiments on real-world datasets and the empirical results validate our theoretical findings.

Federated learning (FL), an emerging distributed machine learning paradigm, in conflux with edge computing is a promising area with novel applications over mobile edge devices. In FL, since mobile devices collaborate to train a model based on their own data under the coordination of a central server by sharing just the model updates, training data is maintained private. However, without the central availability of data, computing nodes need to communicate the model updates often to attain convergence. Hence, the local computation time to create local model updates along with the time taken for transmitting them to and from the server result in a delay in the overall time. Furthermore, unreliable network connections may obstruct an efficient communication of these updates. To address these, in this paper, we propose a delay-efficient FL mechanism that reduces the overall time (consisting of both the computation and communication latencies) and communication rounds required for the model to converge. Exploring the impact of various parameters contributing to delay, we seek to balance the trade-off between wireless communication (to talk) and local computation (to work). We formulate a relation with overall time as an optimization problem and demonstrate the efficacy of our approach through extensive simulations.

Deep learning holds a great promise of revolutionizing healthcare and medicine. Unfortunately, various inference attack models demonstrated that deep learning puts sensitive patient information at risk. The high capacity of deep neural networks is the main reason behind the privacy loss. In particular, patient information in the training data can be unintentionally memorized by a deep network. Adversarial parties can extract that information given the ability to access or query the network. In this paper, we propose a novel privacy-preserving mechanism for training deep neural networks. Our approach adds decaying Gaussian noise to the gradients at every training iteration. This is in contrast to the mainstream approach adopted by Google's TensorFlow Privacy, which employs the same noise scale in each step of the whole training process. Compared to existing methods, our proposed approach provides an explicit closed-form mathematical expression to approximately estimate the privacy loss. It is easy to compute and can be useful when the users would like to decide proper training time, noise scale, and sampling ratio during the planning phase. We provide extensive experimental results using one real-world medical dataset (chest radiographs from the CheXpert dataset) to validate the effectiveness of the proposed approach. The proposed differential privacy based deep learning model achieves significantly higher classification accuracy over the existing methods with the same privacy budget.

Federated learning is a promising tool in the Internet-of-Things (IoT) domain for training a machine learning model in a decentralized manner. Specifically, the data owners (e.g., IoT device consumers) keep their raw data and only share their local computation results to train the global model of the model owner (e.g., an IoT service provider). When executing the federated learning task, the data owners contribute their computation and communication resources. In this situation, the data owners have to face privacy issues where attackers may infer data property or recover the raw data based on the shared information. Considering these disadvantages, the data owners will be reluctant to use their data to participate in federated learning without a well-designed incentive mechanism. In this article, we deliberately design an incentive mechanism jointly considering the task expenditure and privacy issue of federated learning. Based on a differentially private federated learning (DPFL) framework that can prevent the privacy leakage of the data owners, we model the contribution as well as the computation, communication, and privacy costs of each data owner. The three types of costs are data owners' private information unknown to the model owner, which thus forms an information asymmetry. To maximize the utility of the model owner under such information asymmetry, we leverage a 3-D contract approach to design the incentive mechanism. The simulation results validate the effectiveness of the proposed incentive mechanism with the DPFL framework compared to other baseline mechanisms.

Machine learning is increasingly becoming a powerful tool to make decisions in a wide variety of applications, such as medical diagnosis and autonomous driving. Privacy concerns related to the training data and unfair behaviors of some decisions with regard to certain attributes (e.g., sex, race) are becoming more critical. Thus, constructing a fair machine learning model while simultaneously providing privacy protection becomes a challenging problem. In this paper, we focus on the design of classification model with fairness and differential privacy guarantees by jointly combining functional mechanism and decision boundary fairness. In order to enforce ϵ-differential privacy and fairness, we leverage the functional mechanism to add different amounts of Laplace noise regarding different attributes to the polynomial coefficients of the objective function in consideration of fairness constraint. We further propose an utility-enhancement scheme, called relaxed functional mechanism by adding Gaussian noise instead of Laplace noise, hence achieving (ϵ, δ)-differential privacy. Based on the relaxed functional mechanism, we can design (ϵ, δ)-differentially private and fair classification model. Moreover, our theoretical analysis and empirical results demonstrate that our two approaches achieve both fairness and differential privacy while preserving good utility and outperform the state-of-the-art algorithms.

The Alternating Direction Method of Multipliers (ADMM) and its distributed version have been widely used in machine learning. In the iterations of ADMM, model updates using local private data and model exchanges among agents impose critical privacy concerns. Despite some pioneering works to relieve such concerns, differentially private ADMM still confronts many research challenges. For example, the guarantee of differential privacy (DP) relies on the premise that the optimality of each local problem can be perfectly attained in each ADMM iteration, which may never happen in practice. The model trained by DP ADMM may have low prediction accuracy. In this paper, we address these concerns by proposing a novel (Improved) Plausible differentially Private ADMM algorithm, called PP-ADMM and IPP-ADMM. In PP-ADMM, each agent approximately solves a perturbed optimization problem that is formulated from its local private data in an iteration, and then perturbs the approximate solution with Gaussian noise to provide the DP guarantee. To further improve the model accuracy and convergence, an improved version IPP-ADMM adopts sparse vector technique (SVT) to determine if an agent should update its neighbors with the current perturbed solution. The agent calculates the difference of the current solution from that in the last iteration, and if the difference is larger than a threshold, it passes the solution to neighbors; or otherwise the solution will be discarded. Moreover, we propose to track the total privacy loss under the zero-concentrated DP (zCDP) and provide a generalization performance analysis. Experiments on real-world datasets demonstrate that under the same privacy guarantee, the proposed algorithms are superior to the state of the art in terms of model accuracy and convergence rate.

Machine learning has a vast outreach in principal applications and uses large amount of data to train the models, prompting a viable and easy to use Machine Learning as a Service (MLaaS). This flexible paradigm however, could have immense privacy implications since the training data often contains sensitive features, and adversarial access to such models could pose a security risk. In adversarial attacks such as model inversion attack on a system used for face recognition, an adversary uses the output (target label) to reconstruct the input (image of the target individual from the training dataset). To avert such a vulnerability of the system, in this paper, we develop a novel approach of applying perceptual hash to parts of the given training images that leverages the functional mechanism of image hashing. The facial recognition system is then trained over this newly created dataset of perceptually hashed images and high classification accuracy is observed. Furthermore, we demonstrate a series of model inversion attacks emulating adversarial access that yield hashed images of target individuals instead of the original training dataset images; thereby preventing original image reconstruction and counteracting the inversion attack. Through rigorous empirical evaluations of applying the proposed formulation over real world dataset, we verify the effectiveness of our proposed framework in protecting the training image dataset and counteracting inversion attack.

Mobile crowdsensing (MCS) has become a new sensing and computing paradigm due to the proliferation of global positioning system (GPS) enabled mobile devices. There are three parties in the MCS, the MCS server, task requesters and workers. The MCS server needs to collect workers' location information to optimize the task allocation problem. However, during the location data collection process, workers' location privacy might be disclosed without their knowledge. It is challenging to preserve workers' location privacy while effectively and efficiently selecting proper workers to fulfill an MCS task. In this work, we propose a novel differentially private geocoding (DPG) mechanism to preserve workers' location privacy. Specifically, instead of reporting the exact latitude and longitude to the server, workers can use obfuscated geocode to describe their locations, since geocodes can provide an intuitive visualization of workers' spatial information to the MCS server. Based on the workers' obfuscated geocodes, we also formulate a travel distance minimization problem in MCS into an integer linear programming problem. We leverage conditional value at risk (CVaR) to characterize the uncertainty brought by the obfuscated geocodes, and develop feasible solutions to the formulated optimization problem. We conduct simulations with a real-world taxi dataset and verify the effectiveness of the proposed mechanism.

Sparse learning is a very important tool for mining useful information and patterns from high dimensional data. Nonconvex non-smooth regularized learning problems play essential roles in sparse learning, and have drawn extensive attentions recently. We design a family of stochastic proximal gradient methods by applying arbitrary sampling to solve the empirical risk minimization problem with a non-convex and non-smooth regularizer. These methods draw mini-batches of training examples according to an arbitrary probability distribution when computing stochastic gradients. A unified analytic approach is developed to examine the convergence and computational complexity of these methods, allowing us to compare the different sampling schemes. We show that the independent sampling scheme tends to improve performance over the commonly-used uniform sampling scheme. Our new analysis also derives a tighter bound on convergence speed for the uniform sampling than the best one available so far. Empirical evaluations demonstrate that the proposed algorithms converge faster than the state of the art.

To embrace the era of big data, there has been growing interest in designing distributed machine learning to exploit the collective computing power of the local computing nodes. Alternating Direction Method of Multipliers (ADMM) is one of the most popular methods. This method applies iterative local computations over local datasets at each agent and computation results exchange between the neighbors. During this iterative process, data privacy leakage arises when performing local computation over sensitive data. Although many differentially private ADMM algorithms have been proposed to deal with such privacy leakage, they still have to face many challenging issues such as low model accuracy over strict privacy constraints and requiring strong assumptions of convexity of the objective function. To address those issues, in this paper, we propose a differentially private robust ADMM algorithm (PR-ADMM) with Gaussian mechanism. We employ two kinds of noise variance decay schemes to carefully adjust the noise addition in the iterative process and utilize a threshold to eliminate the too noisy results from neighbors. We also prove that PR-ADMM satisfies dynamic zero-concentrated differential privacy (dynamic zCDP) and a total privacy loss is given by (∈, δ)-differential privacy. From a theoretical point of view, we analyze the convergence rate of PR-ADMM for general convex objectives, which is O(1/K) with K being the number of iterations. The performance of the proposed algorithm is evaluated on real-world datasets. The experimental results show that the proposed algorithm outperforms other differentially private ADMM based algorithms under the same total privacy loss.

In recent years, generative adversarial network (GAN) has attracted great attention due to its impressive performance and potential numerous applications, such as data augmentation, real-like image synthesis, image compression improvement, etc. The generator in GAN learns the density of the distribution from real data in order to generate high fidelity fake samples from latent space and deceive the discriminator. Despite its advantages, GAN can easily memorize training samples because of the high model complexity of deep neural networks. Thus, training a GAN with sensitive or private data samples may compromise the privacy of training data. To address this privacy issue, we propose a novel \textit{Privacy Preserving Generative Adversarial Network} (PPGAN) that perturbs the objective function of discriminator by injecting Laplace noises based on functional mechanism to guarantee the differential privacy of training data. Since generator training is considered as a post-processing step while guaranteeing differential privacy of discriminator, the trained generator should be differentially private to effectively protect data samples. Through detailed privacy analysis, we theoretically prove that PPGAN can provide such strict differential privacy guarantee. With extensive simulation study on the benchmark dataset MNIST, we show the efficacy of the proposed PPGAN under practical privacy budgets.

The transportation network company (TNC) services efficiently pair the passengers with the vehicles/drivers through mobile applications, such as Uber, Lyft, Didi, etc. TNC services definitely facilitate the traveling of passengers, while it is equally important to effectively and intelligently schedule the routes of cruising TNC vehicles to improve TNC drivers' revenues. From the TNC drivers' side, the most critical question to address is how to reduce the cruising time, and improve the efficiency/earnings by using their own vehicles to provide TNC services. In this paper, we propose a deep reinforcement learning-based TNC route scheduling approach, which allows the TNC service center to learn about the dynamic TNC service environment and schedule the routes for the vacant TNC vehicles. In particular, we jointly consider multiple factors in the complex TNC environment, such as locations of the TNC vehicles, different time periods during the day, the competition among TNC vehicles, etc., and develop a deep Q-network-based route scheduling algorithm for vacant TNC vehicles based on distributed framework, which makes the server closer to the terminal users and accelerates the training speed. Furthermore, we apply the geo-indistinguishability scheme based on differential privacy to preserve the sensitive location information uploaded by the passengers. We evaluate the proposed algorithm's performance via simulations using open data sets from Didi Chuxing. Through extensive simulations, we show that the proposed scheme is effective in reducing the cruising time of vacant TNC vehicles and improving the earnings of TNC drivers.

The advance in mobile communications has escalated the use of transportation network company (TNC) services by residents. The TNC services efficiently pair the passengers with the vehicles/drivers through mobile applications such as Uber, Lyft, Didi, etc. TNC services definitely facilitate the traveling of passengers, while it is equally important to effectively and intelligently schedule the routes of cruising TNC vehicles to improve TNC drivers' revenues. From the TNC drivers' side, the most critical question to address is how to reduce the cruising time, and improve the efficiency/earnings of using their own vehicles to provide TNC services. In this paper, we propose a deep reinforcement learning based TNC route scheduling approach, which allows the TNC service center to learn about the dynamic TNC service environment and schedule the routes for the vacant TNC vehicles. In particular, we jointly consider multiple factors in the complex TNC environment such as locations of the TNC vehicles, different time periods during the day, the competition among TNC vehicles, etc., and develop a deep Q-network (DQN) based route scheduling algorithm for vacant TNC vehicles. We evaluate the proposed algorithm's performance via simulations using open data sets from Didi Chuxing. Through extensive simulations, we show that the proposed scheme is effective in reducing the cruising time of vacant TNC vehicles and improving the earnings of TNC drivers.