Differential Privacy Techniques Research Articles

Privacy-enhanced generative adversarial network with adaptive noise allocation

Generative adversarial networks (GANs) have become hugely popular by virtue of their impressive ability to generate realistic samples. Although GANs alleviate the arduous data-collection problem, they are prone to memorize training samples as a result of their complex model structure. Thus, GANs may not provide sufficient privacy guarantees, and there is a considerable chance of inadvertently divulging data privacy. To alleviate this issue, we design a privacy-enhanced GAN based on differential privacy. We first integrate truncated concentrated differential privacy technique into GAN for mitigating privacy leakage with tighter privacy bound. Then, according to different privacy demands of users in real-world scenarios, we design two adaptive noise allocation strategies, which enable us to dynamically inject noise into gradients at each iteration. Different strategies provide us with an intuitive handle to adopt a suitable strategy and achieve an elegant compromise between privacy and utility in distinct scenarios. Furthermore, we offer rigorous illustrations from the perspective of privacy preservation and privacy defense to demonstrate that our algorithm can fulfill differential privacy guarantees. Extensive experiments on real-world datasets manifest that our algorithm can generate high-quality samples while achieving an excellent trade-off between model performance and privacy guarantees.

CCM-FL: Covert communication mechanisms for federated learning in crowd sensing IoT

The past decades have witnessed a wide application of federated learning in crowd sensing, to handle the numerous data collected by the sensors and provide the users with precise and customized services. Meanwhile, how to protect the private information of users in federated learning has become an important research topic. Compared with the differential privacy (DP) technique and secure multiparty computation (SMC) strategy, the covert communication mechanism in federated learning is more efficient and energy-saving in training the machine learning models. In this paper, we study the covert communication problem for federated learning in crowd sensing Internet-of-Things networks. Different from the previous works about covert communication in federated learning, most of which are considered in a centralized framework and experimental-based, we firstly proposes a centralized covert communication mechanism for federated learning among n learning agents, the time complexity of which is O(log n), approximating to the optimal solution. Secondly, for the federated learning without parameter server, which is a harder case, we show that solving such a problem is NP-hard and prove the existence of a distributed covert communication mechanism with O(log log Δ log n) times, approximating to the optimal solution. Δ is the maximum distance between any pair of learning agents. Theoretical analysis and numerical simulations are presented to show the performance of our covert communication mechanisms. We hope that our covert communication work can shed some light on how to protect the privacy of federated learning in crowd sensing from the view of communications.

Task-Specific Adaptive Differential Privacy Method for Structured Data.

Data are needed to train machine learning (ML) algorithms, and in many cases often include private datasets that contain sensitive information. To preserve the privacy of data used while training ML algorithms, computer scientists have widely deployed anonymization techniques. These anonymization techniques have been widely used but are not foolproof. Many studies showed that ML models using anonymization techniques are vulnerable to various privacy attacks willing to expose sensitive information. As a privacy-preserving machine learning (PPML) technique that protects private data with sensitive information in ML, we propose a new task-specific adaptive differential privacy (DP) technique for structured data. The main idea of the proposed DP method is to adaptively calibrate the amount and distribution of random noise applied to each attribute according to the feature importance for the specific tasks of ML models and different types of data. From experimental results under various datasets, tasks of ML models, different DP mechanisms, and so on, we evaluate the effectiveness of the proposed task-specific adaptive DP method. Thus, we show that the proposed task-specific adaptive DP technique satisfies the model-agnostic property to be applied to a wide range of ML tasks and various types of data while resolving the privacy-utility trade-off problem.

Intrusion Detection Based on Privacy-Preserving Federated Learning for the Industrial IoT

Federated learning (FL) has attracted significant interest given its prominent advantages and applicability in many scenarios. However, it has been demonstrated that sharing updated gradients/weights during the training process can lead to privacy concerns. In the context of the Internet of Things (IoT), this can be exacerbated due to intrusion detection systems (IDSs), which are intended to detect security attacks by analyzing the devices’ network traffic. Our work provides a comprehensive evaluation of differential privacy techniques, which are applied during the training of an FL-enabled IDS for industrial IoT. Unlike previous approaches, we deal with nonindependent and identically distributed data over the recent ToN_IoT dataset, and compare the accuracy obtained considering different privacy requirements and aggregation functions, namely FedAvg and the recently proposed Fed+. According to our evaluation, the use of Fed+ in our setting provides similar results even when noise is included in the federated training process.

Differential Privacy-Enabled Multi-Party Learning with Dynamic Privacy Budget Allocating Strategy

As one of the promising paradigms of decentralized machine learning, multi-party learning has attracted increasing attention, owing to its capability of preventing the privacy of participants from being directly exposed to adversaries. Multi-party learning enables participants to train their model locally without uploading private data to a server. However, recent studies have shown that adversaries may launch a series of attacks on learning models and extract private information about participants by analyzing the shared parameters. Moreover, existing privacy-preserving multi-party learning approaches consume higher total privacy budgets, which poses a considerable challenge to the compromise between privacy guarantees and model utility. To address this issue, this paper explores an adaptive differentially private multi-party learning framework, which incorporates zero-concentrated differential privacy technique into multi-party learning to get rid of privacy threats, and offers sharper quantitative results. We further design a dynamic privacy budget allocating strategy to alleviate the high accumulation of total privacy budgets and provide better privacy guarantees, without compromising the model’s utility. We inject more noise into model parameters in the early stages of model training and gradually reduce the volume of noise as the direction of gradient descent becomes more accurate. Theoretical analysis and extensive experiments on benchmark datasets validated that our approach could effectively improve the model’s performance with less privacy loss.

A Systematic Survey for Differential Privacy Techniques in Federated Learning

Federated learning is a distributed machine learning technique that trains a global model by exchanging model parameters or intermediate results among multiple data sources. Although federated learning achieves physical isolation of data, the local data of federated learning clients are still at risk of leakage under the attack of malicious individuals. For this reason, combining data protection techniques (e.g., differential privacy techniques) with federated learning is a sure way to further improve the data security of federated learning models. In this survey, we review recent advances in the research of differentially-private federated learning models. First, we introduce the workflow of federated learning and the theoretical basis of differential privacy. Then, we review three differentially-private federated learning paradigms: central differential privacy, local differential privacy, and distributed differential privacy. After this, we review the algorithmic optimization and communication cost optimization of federated learning models with differential privacy. Finally, we review the applications of federated learning models with differential privacy in various domains. By systematically summarizing the existing research, we propose future research opportunities.

An Agile Privacy-Preservation Solution for IoT-Based Smart City Using Different Distributions

In today's world, everything is connected via the Internet. Smart cities are one application of the Internet of Things (IoT) that is aimed at making city management more efficient and effective. However, IoT devices within a smart city may collect sensitive information. Protecting sensitive information requires maintaining privacy. Existing smart city solutions have been shown not to offer effective privacy protection. We propose a novel continuous method called Differential Privacy-Preserving Smart City (DPSmartCity). When the IoT device produces sensitive data, it applies differential privacy techniques as a privacy-preserving method that uses Laplace distributions or exponential distributions. The controller receives the perturbed data and forwards it to the SDN. SDN controllers eventually send the data to the cloud for further analysis. Accordingly, if the data is not sensitive, it is directly uploaded to the cloud. In this way, DPSmartCity provides a dynamic environment from the point of view of privacy preservation. As a result, adversaries are unable to easily compromise the privacy of the devices. The solution incurs at most 10-18% overhead on IoT devices. Our solution can therefore be used for IoT devices that are capable of handling this overhead.

Seeing is believing: Towards interactive visual exploration of data privacy in federated learning

Federated learning (FL), as a popular distributed machine learning paradigm, has driven the integration of knowledge in ubiquitous data owners under one roof. Although designed for privacy-preservation by nature, the supposed well-sanitized parameters still convey sensitive information (e.g., reconstruction attack), while existing technical countermeasures provide weak explainability for privacy understanding and protection practices of general users. This work investigates these privacy concerns with an exploratory study and elaborates on data owners’ expectations in FL. Based on the analysis, we design the first interactive visualization system for FL privacy that supports intelligible privacy inspection and adjustment for data owners. Specifically, our proposal facilitates sample recommendation for joint privacy–performance training at cold start. Then it provides visual interpretation and attention rendering of privacy risks in view of multiple attacking channels and a holistic view. Further it supports interactive privacy enhancement involving both user initiative and differential privacy technique, and iterative trade-off with real-time inference accuracy estimation. We evaluate the effectiveness of the system and collect qualitative feedbacks from users. The results demonstrate that 96.7% of users acknowledge the benefits to privacy inspection and adjustment and 90.3% are willing to use our system. More importantly, 87.1% increase the willingness of contributing data for FL.

Differentially Private Tripartite Intelligent Matching Against Inference Attacks in Ride-Sharing Services

In intelligent transportation systems, the key issue of the Ride-Sharing Service (RSS) is to find proper drivers for the passengers by Intelligent Matching (IM) of two or three objects, including the positions of drivers, the travel information of passengers, and the spots where passengers and drivers meet and separate. Unfortunately, the exposure of travel plans of passengers in the IM process due to inference attacks has raised concerns about the privacy violation. To resist the inference attacks, we propose a Differentially Private Tripartite IM (DPTIM) protocol for RSS. DPTIM is based on the tripartite IM process, which intelligently finds the suitable threshold to filter out the matched objects with satisfaction scores below the threshold, so as to provide the high average satisfaction score of matched passengers. Compared to existing relevant mechanisms, DPTIM is distinguished by the feature that it leverages the inference error and differential privacy techniques to prevent the prior-information-based inference attacks and constrain the posterior information leakage, while providing satisfactory matching results. Furthermore, DPTIM meets the personalized demand of location privacy by using the passenger-specific tolerance estimation on inference errors and the personalized privacy budget. Finally, we implement DPTIM on real-world datasets, and demonstrate the satisfactory performance of DPTIM in terms of the average satisfaction score of passengers, the anti-inference-attack capability, and the passenger-specific privacy requirement.

PADP-FedMeta: A personalized and adaptive differentially private federated meta learning mechanism for AIoT

Powered by edge computing, the last few years have seen a rapid growth in AIoT applications. Federated learning (FL), as a typical machine learning framework for edge intelligence, has attracted a large number of attention since it can protect user privacy. However, recent studies have shown that FL cannot fully ensure privacy. To address this, differential privacy technique is widely used in FL. Nevertheless, existing works neglect that data on devices are non-independent and identically distributed (Non-IID), which largely degrades model accuracy and convergence speed. In this paper, we propose PADP-FedMeta, a personalized and adaptive differentially private federated meta learning mechanism with a provable privacy and convergence guarantee. PADP-FedMeta mitigates the negative effect of Non-IID upon model accuracy by introducing federated meta learning, and significantly improves the convergence speed with an adaptive privacy parameter. Comprehensive experimental results show the effectiveness of our mechanism and its superior performance over the state-of-the-art differentially private FL schemes.

LbSP: Load-Balanced Secure and Private Autonomous Electric Vehicle Charging Framework With Online Price Optimization

Nowadays, autonomous electric vehicles (AEVs) are increasingly popular due to low resource consumption, low pollutant emission, and high efficiency. In practice, Vehicle-to-Grid (V2G) networks supply energy power to EVs to ensure the usage of EVs. However, there are still certain security and privacy concerns in V2G connections, such as identity impersonation and message manipulation. Additionally, the widespread usage of EVs brings significant pressure on the power grid, leading to undesirable effects like voltage deviations if EVs’ charging is not well coordinated. In this article, to tackle these issues, we design a novel load-balanced secure and private EV charging framework named load-balanced secure and private framework (LbSP) for secure, private, and efficient EV charging with a minimal negative effect on the existing power grid. It assures reliable and efficient charging services by a lightweighted encryption technique. Also, it balances the energy consumption of power grids via an online pricing strategy that minimizes load variance by optimizing energy prices in real time. Moreover, it preserves users’ privacy while not affecting online pricing using an advanced differential privacy technique. Furthermore, LbSP deploys on an edge-cloud structure for fast response and more precise pricing, where clouds balance overall load consumption by online price optimization while edges gather data for clouds and respond to charging requests from EVs. The evaluation results show that the proposed framework ensures secure and private EV charging, balances energy load consumption, and preserves users’ privacy.

Privacy-Preserving Prediction of Victim’s Mortality and Their Need for Transportation to Health Facilities

Emergency medical services (EMS) provide crucial prehospital care, such as in the case of cardiac arrest, where the victim requires immediate first-aid. For this reason, it is vital to improving EMS response time. This article proposes a novel methodology based on machine learning (ML) techniques to predict both the victims’ mortality and their need for transportation to health facilities using data gathered from the start of the emergency call until the Departmental Fire and Rescue Service of the Doubs (SDIS25) is notified. We first analyzed SDIS25 calls to find out associations between the call processing times and victims’ mortality, and to measure the variables’ importance. Next, we validated our proposed ML-based methodology, where mortality could be predicted with accuracy and area under the receiver operating characteristic curve (AUC) scores of 96.44% and 96.04%, respectively, while the need for transportation achieved an accuracy and AUC scores of 73.62% and 78.91%, respectively. What is more, we found out that it was still possible to predict both targets perturbating the input data by applying <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> -anonymity and differential privacy techniques. In conclusion, the results showed the potential of ML for EMS, which can be used as a decision-support tool to early identify mortality and the use of resources (transportation) and, thus, help EMS to save more lives and avoid service disruptions.

Optimized setting of privacy budget in a recommendation system with local differential privacy

Recommendation system can help users find the data they need from the massive amounts of data. At the same time, uploading original user data to the server may reveal user privacy. We utilize local differential privacy techniques to provide privacy protection for users in the recommendation system. In the local differential privacy model, the degree of privacy protection is measured by the privacy budget, and a high privacy budget usually means high analysis accuracy. To help users minimize privacy loss and maximize recommendation accuracy, we model the privacy budget setting problem as a multiarmed bandit problem and propose the upper confidence bound learning policy to help each user choose the privacy budget. Considering that users have different sensitivity levels to different data, we modify the above policy. Experimental results reveal that the proposed policy can help users choose an appropriate privacy budget, which can effectively increase the total user payoff.

Local Trajectory Privacy Protection in 5G Enabled Industrial Intelligent Logistics

The value of trajectory data lies mainly in the spatio-temporal correlation. However, the existing privacy protection methods ignore the spatio-temporal correlation of trajectory data, resulting in a large error in trajectory proportion estimation and Top-K classification. For the privacy of truck trajectory in intelligent logistics, the location and trajectory data perturbation method based on quadtree indexing is proposed, which leverages location generalization and local differential privacy techniques. Our proposed algorithms are suitable for datasets with a large sample space and can protect the trajectory privacy of truck drivers while preserving the strong correlation between adjacent spatio-temporal nodes in the trajectory. The results of simulation on a real trajectory dataset show that the proposed methods not only meet the trajectory privacy requirements of users but also have a good performance in trajectory proportion estimation and Top-K classification.

A differentially private nonnegative matrix factorization for recommender system

Nonnegative matrix factorization (NMF)-based models have been proven to be highly effective and scalable in addressing collaborative filtering (CF) problems in the recommender system (RS). Since RS requires tremendous user data to provide personalized information services, the issue of data privacy has gained prominence. Although the differential privacy (DP) technique has been widely applied to RS, the requirement of nonnegativity makes it difficult to successfully incorporate DP into NMF. In this paper, a differentially private NMF (DPNMF) method is proposed by perturbing the coefficients of the polynomial expression of the objective function, which achieves a good trade-off between privacy protection and recommendation quality. Moreover, to alleviate the influence of the noises added by DP on the items with sparse ratings, an imputation-based DPNMF (IDPNMF) method is proposed. Theoretic analyses and experimental results on several benchmark datasets show that the proposed schemes have good performance and can achieve better recommendation quality on large-scale datasets. Therefore, our schemes have high potential to implement privacy-preserving RS based on big data.

Private True Data Mining: Differential Privacy Featuring Errors to Manage Internet-of-Things Data

Available data may differ from true data in many cases due to sensing errors, especially for the Internet of Things (IoT). Although privacy-preserving data mining has been widely studied during the last decade, little attention has been paid to data values containing errors. Differential privacy, which is the de facto standard privacy metric, can be achieved by adding noise to a target value that must be protected. However, if the target value already contains errors, there is no reason to add extra noise. In this paper, a novel privacy model called true-value-based differential privacy (TDP) is proposed. This model applies traditional differential privacy to the “true value” unknown by the data owner or anonymizer but not to the “measured value” containing errors. Based on TDP, the amount of noise added by differential privacy techniques can be reduced by approximately 20% by our solution. As a result, the error of generated histograms can be reduced by 40.4% and 29.6% on average according to mean square error and Jensen–Shannon divergence, respectively. We validate this result on synthetic and five real data sets. Moreover, we proved that the privacy protection level does not decrease as long as the measurement error is not overestimated.

Differential Privacy Protection of Face Images Based on Region Growing

Face images, as an information carrier, are rich in sensitive information. Direct publication of these images would cause privacy leak, due to their natural weak privacy. Most of the existing privacy protection methods for face images adopt data publication under a non-interactive framework. However, the E-effect under this framework covers the entire image, such that the noise influence is uniform across the image. To solve the problem, this paper proposes region growing publication (RGP), an algorithm for the interactive publication of face images under differential privacy. This innovative algorithm combines the region growing technique with differential privacy technique. The privacy budget E is dynamically allocated, and the Laplace noise is added, according to the similarity between adjacent sub-images. To measure this similarity more effectively, the fusion similarity measurement mechanism (FSMM) was designed, which better adapts to the intrinsic attributes of images. Different from traditional region growing rules, the FSMM fully considers various attributes of images, including brightness, contrast, structure, color, texture, and spatial distribution. To further enhance algorithm feasibility, RGP was extended to atypical region growing publication (ARGP). While RGP limits the region growing direction between adjacent sub-images, ARGP searches for the qualified sub-images across the image, with the aid of the exponential mechanism, thereby expanding the region merging scope of the seed point. The results show that our algorithm can satisfy E-differential privacy, and the denoised image still have a high availability.

Toward a Comparison of Classical and New Privacy Mechanism.

In the last decades, the development of interconnectivity, pervasive systems, citizen sensors, and Big Data technologies allowed us to gather many data from different sources worldwide. This phenomenon has raised privacy concerns around the globe, compelling states to enforce data protection laws. In parallel, privacy-enhancing techniques have emerged to meet regulation requirements allowing companies and researchers to exploit individual data in a privacy-aware way. Thus, data curators need to find the most suitable algorithms to meet a required trade-off between utility and privacy. This crucial task could take a lot of time since there is a lack of benchmarks on privacy techniques. To fill this gap, we compare classical approaches of privacy techniques like Statistical Disclosure Control and Differential Privacy techniques to more recent techniques such as Generative Adversarial Networks and Machine Learning Copies using an entire commercial database in the current effort. The obtained results allow us to show the evolution of privacy techniques and depict new uses of the privacy-aware Machine Learning techniques.

SP-CIDS: Secure and Private Collaborative IDS for VANETs

Vehicular Ad hoc NETworks (VANETs) serve as the backbone of Intelligent Transportation Systems (ITS), providing passengers with safety and comfort. However, VANETs are vulnerable to major threats that affect data privacy and network services either from an individual or distributed attacker. In this paper, a Secure and Private-Collaborative Intrusion Detection System (SP-CIDS) is proposed to detect network attacks and to mitigate security concerns. In SP-CIDS, a Distributed Machine Learning (DML) model based on the Alternating Direction Method of Multipliers (ADMM) is used, which leverages the potential of vehicle-to-vehicle collaboration in the learning process to improve the storage efficiency, accuracy, and scalability of the IDS. However, there are significant data privacy concerns possible in such collaboration, where a CIDS can act as a malicious system that has access to the intermediate stages of the learning process. Additionally, the SP-CIDS system uses Differential Privacy (DP) technique to address the aforementioned data privacy risk associated with the DML-based CIDS. The SP-CIDS system is evaluated with logistic regression, naïve bayes, and ensemble classifiers. Simulation results substantiate that a private ensemble classifier secures the training data with DP and also achieves 96.94% accuracy.

Parking recommender system privacy preservation through anonymization and differential privacy

AbstractRecent advancements in the Internet of Things (IoT) have enabled the development of smart parking systems that use services of third‐party parking recommender system to provide recommendations of personalized parking spot to users based on their past experience. However, the indiscriminate sharing of users' data with an untrusted (or semitrusted) parking recommender system may breach the privacy because users' behavior and mobility patterns could be inferred by analyzing their past history. Therefore, in this article, we present two solutions that preserve privacy of users in parking recommender systems while analyzing the past parking history using k‐anonymity (anonymization) and differential privacy (perturbation) techniques. Specifically, given an original parking database containing users' parking information, the k‐anonymity mechanism constructs an anonymized database, while differential privacy perturbs the query response using the Laplace mechanism, making the users indistinguishable in both approaches, hence preserving the privacy. Experimental results on a data set constructed from real parking measurements evaluate the trade‐off between privacy and utility, therefore enabling users to receive parking spots recommendations while preserving their privacy.