Laplace Mechanism Research Articles

Where Am I Parking: Incentive Online Parking-Space Sharing Mechanism With Privacy Protection

Sharing private parking spaces during their idle time periods has shown great potential for addressing urban traffic congestion and illegitimate parking problems in smart cities. In this article, aiming to address the online parking-space sharing issue while ensuring the privacy of customer parking destination locations, we propose a novel destination privacy-preserving online parking sharing (DPOPS) incentive scheme. In particular, the online parking-space sharing problem is formalized as a social welfare maximization problem in a two-sided market, where parking-space providers (PSPs) and customers are regarded as sellers and buyers. Then, novel threshold value-based rules are designed to determine winners, payments, and reimbursement. Finally, winners are matched by solving a mixed-integer nonlinear programming problem, aiming to minimize the distance between customer’s destination and allocated parking space. In addition, the location privacy of the customers’ destinations is protected by the Laplace mechanism. We prove that DPOPS achieves several economically effective properties and approximate differential privacy. We analyze the upper bound of the efficiency loss of our scheme. Extensive evaluation results demonstrate that our scheme can not only achieve good performance regarding social welfare, PSP satisfaction ratio, privacy preservation, and computation overhead but also leads to shorter travel distances for customers comparing to the baseline scheme. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —In this article, we address the online parking-space sharing issue with considering the parking-space providers (PSPs) and customers’ individual utility while preserving the location privacy of customers’ destinations. Most of the previous works focused on designing a centralized mechanism for allocating parking spaces without considering the protection of the customers’ location privacy. In particular, we propose an online parking-space sharing scheme called DPOPS, including a novel threshold value-based winner determination rule and a parking-space allocation rule. The proposed scheme DPOPS allows the PSPs and customers submit their bids and asks according to their own willingness and is able to improve the utilization of private parking spaces during their idle time periods. Moreover, the location privacy of customers’ destinations is protected by the Laplace mechanism. The experiments demonstrate that the proposed approach outperforms the exponential-based scheme in terms of PSP satisfaction ratio and the travel distance for parking-space customer. The proposed scheme is helpful in managing the vacant parking space in a competitive market and can be readily implemented in the real-world online parking-space sharing systems.

Offset-Symmetric Gaussians for Differential Privacy

The Gaussian distribution is widely used in mechanism design for differential privacy (DP). Thanks to its sub-Gaussian tail, it significantly reduces the chance of outliers when responding to queries. However, it can only provide approximate (&#x03B5;,&#x03B4;(&#x03B5;))-DP. In practice, &#x03B4;(&#x03B5;) must be much smaller than the size of the dataset, which may limit the use of the Gaussian mechanism for large datasets with strong privacy requirements. In this paper, we introduce and analyze a new distribution for use in DP that is based on the Gaussian distribution, but has improved privacy performance. The so-called offset-symmetric Gaussian tail (OSGT) distribution is obtained through using the normalized tails of two symmetric Gaussians around zero. Consequently, it can still have sub-Gaussian tail and lend itself to analytical derivations. We analytically derive the variance of the OSGT random variable and &#x03B4;(&#x03B5;) of the single-dimensional OSGT mechanism. We extend the OSGT mechanism to <i>k</i>-dimensional queries, iteratively compute its &#x03B4;_<i>k</i>(&#x03B5;), derive its R&#x00E9;nyi differential privacy, and study its composition. Numerical results show the OSGT mechanism can offer better privacy-utility performance compared to the Gaussian and Laplace mechanisms. We also derive a method for post processing the output of the OSGT mechanism to approximate the query based on the minimum mean square error (MMSE) estimation technique. The simulation results of such processing confirm the efficacy of the OSGT mechanism over the Gaussian mechanism.

Inference for Optimal Differential Privacy Procedures for Frequency Tables

When releasing data to the public, a vital concern is the risk of exposing personal information of the individuals who have contributed to the data set. Many mechanisms have been proposed to protect individual privacy, though less attention has been dedicated to practically conducting valid inferences on the altered privacy-protected data sets. For frequency tables, the privacy-protection-oriented perturbations often lead to negative cell counts. Releasing such tables can undermine users’ confidence in the usefulness of such data sets. This paper focuses on releasing one-way frequency tables. We recommend an optimal mechanism that satisfies ϵ-differential privacy (DP) without suffering from having negative cell counts. The procedure is optimal in the sense that the expected utility is maximized under a given privacy constraint. Valid inference procedures for testing goodness-of-fit are also developed for the DP privacy-protected data. In particular, we propose a de-biased test statistic for the optimal procedure and derive its asymptotic distribution. In addition, we also introduce testing procedures for the commonly used Laplace and Gaussian mechanisms, which provide a good finite sample approximation for the null distributions. Moreover, the decaying rate requirements for the privacy regime are provided for the inference procedures to be valid. We further consider common users’ practices such as merging related or neighboring cells or integrating statistical information obtained across different data sources and derive valid testing procedures when these operations occur. Simulation studies show that our inference results hold well even when the sample size is relatively small. Comparisons with the current field standards, including the Laplace, the Gaussian (both with/without post-processing of replacing negative cell counts with zeros), and the Binomial-Beta McClure-Reiter mechanisms, are carried out. In the end, we apply our method to the National Center for Early Development and Learning’s (NCEDL) multi-state studies data to demonstrate its practical applicability.

Privately Publishing Internet of Things Data: Bring Personalized Sampling Into Differentially Private Mechanisms

Massive Internet of Things (IoT) data sets are possessed by big institutions serving daily life because IoT devices are widely used in our daily life such as wearable devices and smart home devices. Publishing these data sets among various institutions causes an increasing number of users to concern their personal privacy. Differential privacy is the state-of-the-art concept of privacy preservation, but it suffers from the low accuracy. In this article, we improve differentially private mechanisms including the Laplace mechanism as well as the sample and aggregation mechanism by bringing the personalized sampling technology into these mechanisms so that IoT data sets can be privately published through differentially private mechanisms. In particular, improved mechanisms assign a personalized sampling probability to each data record in a way that their accuracy can be improved. We analyse improved mechanisms in terms of their privacy and accuracy. Then, we empirically demonstrate that the performance of improved mechanisms is better than original mechanisms through extensive experiments on synthetic data sets and real-world data sets.

Differential Privacy in Social Networks Using Multi-Armed Bandit

There has been an exponential growth over the years in the number of users connected to social networks. This has spurred research interest in social networks to ensure the privacy of users. From a theoretical standpoint, a social network is modeled as a directed graph network and interactions among agents in the directed graph network can be analyzed with non-Bayesian learning and online learning strategies. The goal of the agents is to learn the underlying time-varying true state of the network through repeated cooperative interaction among themselves. To overcome privacy challenges in social networks, recent research works include differential privacy in the social network analysis to guarantee the privacy of shared information among the agents. However, the common online learning strategy adopted in most existing work is the stochastic multi-armed bandit approach which assumes that the loss distribution is independent and identically distributed. This does not account for the arbitrariness of the time-varying true state in the social network. Therefore, this paper proposes a tougher but realistic setting that removes the restriction on the loss distribution. Two non-stochastic multi-armed bandit algorithms are proposed. The first algorithm uses the Laplace mechanism to guarantee differential privacy against a third-party intruder. The second algorithm uses the Laplace mechanism to guarantee differential privacy against both a third-party intruder and any spying agent in the network. The simulation results show that the agents’ beliefs converge to the most dominant true state among the sequence of arbitrarily time-varying true states over the time horizon. The speed of convergence comes as a trade-off with privacy. Regret bounds are obtained for the proposed algorithms and compared to the non-private algorithm in the literature.

Non-Global Privacy Protection Facing Sensitive Areas in Face Images

Face images, as an information carrier, are naturally weak in privacy. If they are collected and analyzed by malicious third parties, personal privacy will leak, and many other unmeasurable losses will occur. Differential privacy protection of face images is mainly being studied under non-interactive frameworks. However, the ε-effect impacts the entire image under these frameworks. Besides, the noise influence is uniform across the protected image, during the realization of the Laplace mechanism. The differential privacy of face images under interactive mechanisms can protect the privacy of different areas to different degrees, but the total error is still constrained by the image size. To solve the problem, this paper proposes a non-global privacy protection method for sensitive areas in face images, known as differential privacy of landmark positioning (DPLP). The proposed algorithm is realized as follows: Firstly, the active shape model (ASM) algorithm was adopted to position the area of each face landmark. If the landmark overlaps a subgraph of the original image, then the subgraph would be taken as a sensitive area. Then, the sensitive area was treated as the seed for regional growth, following the fusion similarity measurement mechanism (FSMM). In our method, the privacy budget is only allocated to the seed; whether any other insensitive area would be protected depends on whether the area exists in a growing region. In addition, when a subgraph meets the criterion for merging with multiple seeds, the most reasonable seed to be merged would be selected by the exponential mechanism. Experimental results show that the DPLP algorithm satisfies ε-differential privacy, its total error does not change with image size, and the noisy image remains highly available.

Differentially Private Kernel Support Vector Machines Based on the Exponential and Laplace Hybrid Mechanism

Support vector machines (SVMs) are among the most robust and accurate methods in all well-known machine learning algorithms, especially for classification. The SVMs train a classification model by solving an optimization problem to decide which instances in the training datasets are the support vectors (SVs). However, SVs are intact instances taken from the training datasets and directly releasing the classification model of the SVMs will carry significant risk to the privacy of individuals, when the training datasets contain sensitive information. In this paper, we study the problem of how to release the classification model of kernel SVMs while preventing privacy leakage of the SVs and satisfying the requirement of privacy protection. We propose a new differentially private algorithm for the kernel SVMs based on the exponential and Laplace hybrid mechanism named DPKSVMEL. The DPKSVMEL algorithm has two major advantages compared with existing private SVM algorithms. One is that it protects the privacy of the SVs by postprocessing and the training process of the non-private kernel SVMs does not change. Another is that the scoring function values are directly derived from the symmetric kernel matrix generated during the training process and does not require additional storage space and complex sensitivity analysis. In the DPKSVMEL algorithm, we define a similarity parameter to denote the correlation or distance between the non-SVs and every SV. And then, every non-SV is divided into a group with one of the SVs according to the maximal value of the similarity. Under some certain similarity parameter value, we replace every SV with a mean value of the top-k randomly selected most similar non-SVs within the group by the exponential mechanism if the number of non-SVs is greater than k. Otherwise, we add random noise to the SVs by the Laplace mechanism. We theoretically prove that the DPKSVMEL algorithm satisfies differential privacy. The extensive experiments show the effectiveness of the DPKSVMEL algorithm for kernel SVMs on real datasets; meanwhile, it achieves higher classification accuracy than existing private SVM algorithms.

Privacy-Preserving Aggregation for Federated Learning-Based Navigation in Vehicular Fog

Federated learning-based automotive navigation has recently received considerable attention, as it can potentially address the issue of weak global positioning system (GPS) signals under severe blockages, such as in downtowns and tunnels. Specifically, the data-driven navigation framework combines the position estimation offered by the high-sampling inertial measurement units and the position calibration provided by the low-sampling GPS signals. Despite its promise, the privacy preservation and flexibility of the participating users in the federated learning process are still problematic. To address these challenges, in this article, we propose an efficient, flexible, and privacy-preserving model aggregation scheme under a federated learning-based navigation framework named FedLoc. Specifically, our proposed scheme efficiently protects the locally trained model updates, flexibly supports the fluctuation of participants, and is robust against unregistered malicious users by exploiting a homomorphic threshold cryptosystem, together with the bounded Laplace mechanism and the skip list. We perform a detailed security analysis to demonstrate the security properties in terms of privacy preservation and dishonest user detection. In addition, we evaluate and compare the computational efficiency with two traditional schemes, and the simulation results show that our scheme greatly improves the computational efficiency during participant fluctuation. To validate the effectiveness of our scheme, we also show that only part of the model update is excluded from aggregation in the case of a dishonest user.

Emphasizing privacy and security of edge intelligence with machine learning for healthcare

PurposeArtificial Intelligence (AI) has surpassed expectations in opening up different possibilities for machines from different walks of life. Cloud service providers are pushing. Edge computing reduces latency, improving availability and saving bandwidth.Design/methodology/approachThe exponential growth in tensor processing unit (TPU) and graphics processing unit (GPU) combined with different types of sensors has enabled the pairing of medical technology with deep learning in providing the best patient care. A significant role of pushing and pulling data from the cloud, big data comes into play as velocity, veracity and volume of data with IoT assisting doctors in predicting the abnormalities and providing customized treatment based on the patient electronic health record (EHR).FindingsThe primary focus of edge computing is decentralizing and bringing intelligent IoT devices to provide real-time computing at the point of presence (PoP). The impact of the PoP in healthcare gains importance as wearable devices and mobile apps are entrusted with real-time monitoring and diagnosis of patients. The impact edge computing of the PoP in healthcare gains significance as wearable devices and mobile apps are entrusted with real-time monitoring and diagnosis of patients.Originality/valueThe utility value of sensors data improves through the Laplacian mechanism of preserved PII response to each query from the ODL. The scalability is at 50% with respect to the sensitivity and preservation of the PII values in the local ODL.

DPLQ: Location‐based service privacy protection scheme based on differential privacy

The existing privacy protection schemes for Location-Based Service (LBS) only protect users' location privacy or query privacy, which can not adopt both of the privacy protections simultaneously in the LBS system. Moreover, these schemes cannot take into account the spatial-temporal correlation and background knowledge. In response to the above mentioned questions, the LBS Privacy Protection Scheme Based on Differential Privacy (DPLQ) is proposed. The method contains two kinds of privacy protection algorithms: users' location privacy protection algorithm and users' query privacy protection algorithm. The users' location privacy protection algorithm divides the map using the Voronoi diagram, choosing l fake location points based on the improved k-means algorithm and l-diversity idea, and protects users' location privacy with the Laplace mechanism. Based on the k-anonymous algorithm, the users' query privacy protection algorithm builds a query k-anonymous set according to the neighbour users' query requests at the same time t in the cluster and the historical query probability of the region’s POI and protects users' query privacy with the exponential mechanism. Through setting the privacy protection intensity of the algorithm by the users, the generated location dataset and query k-anonymous set can resist a variety of attacks from malicious attackers. Theoretical analysis and experimental results show that the scheme can effectively protect the location privacy and query privacy of users.

Differentially private distributed online learning over time‐varying digraphs via dual averaging

AbstractThis article investigates a distributed online learning problem with privacy preservation, in which the learning nodes in a distributed network aims to minimize the sum of local loss functions over time horizon . Based on the push‐sum protocol and the Laplace mechanism, we propose a differentially private distributed dual averaging algorithm for constrained distributed online learning problem over time‐varying digraphs. It is shown that the expectation of the regret of our algorithm achieves a sublinear rate of . Furthermore, we provide an analysis of differential privacy, which reveals a tradeoff between the accuracy and the privacy level of our algorithm. Finally, numerical examples are presented to validate the effectiveness of the algorithm.

Differentially private density estimation with skew-normal mixtures model

The protection of private data is a hot research issue in the era of big data. Differential privacy is a strong privacy guarantees in data analysis. In this paper, we propose DP-MSNM, a parametric density estimation algorithm using multivariate skew-normal mixtures (MSNM) model to differential privacy. MSNM can solve the asymmetric problem of data sets, and it is could approximate any distribution through expectation–maximization (EM) algorithm. In this model, we add two extra steps on the estimated parameters in the M step of each iteration. The first step is adding calibrated noise to the estimated parameters based on Laplacian mechanism. The second step is post-processes those noisy parameters to ensure their intrinsic characteristics based on the theory of vector normalize and positive semi definition matrix. Extensive experiments using both real data sets evaluate the performance of DP-MSNM, and demonstrate that the proposed method outperforms DPGMM.

TIDY: Publishing a Time Interval Dataset With Differential Privacy

Log data from mobile devices generally contain a series of events with temporal information including time intervals which consist of the start and finish times. However, the problem of releasing differentially private time interval datasets has not been tackled yet. A time interval dataset can be represented by a two dimensional (2D) histogram. Most of the methods to publish 2D histograms partition the data into rectangular spaces to reduce the aggregated noise error for range queries. However, the existing algorithms to publish 2D histograms suffer from the structural error when applied to time interval datasets. To reduce the aggregated noise errors and suppress the increase in the structural error, we propose the TIDY (publishing Time Intervals via Differential privacY) algorithm. We use the frequency vectors as a compact representation of the time interval dataset. After applying the Laplace mechanism to the frequency vectors, we improve the utility of the frequency vectors based on a maximum likelihood estimation. We also develop a new partitioning method adapted for the frequency vectors to balance the trade-off between the noise and structural errors. Our empirical study on real-life and synthetic datasets confirms that TIDY outperforms the existing algorithms for 2D histograms.

Differential identifiability clustering algorithms for big data analysis

Individual privacy preservation has become an important issue with the development of big data technology. The definition of ρ-differential identifiability (DI) precisely matches the legal definitions of privacy, which can provide an easy parameterization approach for practitioners so that they can set privacy parameters based on the privacy concept of individual identifiability. However, differential identifiability is currently only applied to some simple queries and achieved by Laplace mechanism, which cannot satisfy complex privacy preservation issues in big data analysis. In this paper, we propose a new exponential mechanism and composition properties of differential identifiability, and then apply differential identifiability to k-means and k-prototypes algorithms on MapReduce framework. DI k-means algorithm uses the usual Laplace mechanism and composition properties for numerical databases, while DI k-prototypes algorithm uses the new exponential mechanism and composition properties for mixed databases. The experimental results show that both DI k-means and DI k-prototypes algorithms satisfy differential identifiability.

Obfuscation of images via differential privacy: From facial images to general images

Due to the pervasiveness of image capturing devices in every-day life, images of individuals are routinely captured. Although this has enabled many benefits, it also infringes on personal privacy. A promising direction in research on obfuscation of facial images has been the work in the k-same family of methods which employ the concept of k-anonymity from database privacy. However, there are a number of deficiencies of k-anonymity that carry over to the k-same methods, detracting from their usefulness in practice. In this paper, we first outline several of these deficiencies and discuss their implications in the context of facial obfuscation. We then develop a framework through which we obtain a formal differentially private guarantee for the obfuscation of facial images in generative machine learning models. Our approach provides a provable privacy guarantee that is not susceptible to the outlined deficiencies of k-same obfuscation and produces photo-realistic obfuscated output. In addition, we demonstrate through experimental comparisons that our approach can achieve comparable utility to k-same obfuscation in terms of preservation of useful features in the images. Furthermore, we propose a method to achieve differential privacy for any image (i.e., without restriction to facial images) through the direct modification of pixel intensities. Although the addition of noise to pixel intensities does not provide the high visual quality obtained via generative machine learning models, it offers greater versatility by eliminating the need for a trained model. We demonstrate that our proposed use of the exponential mechanism in this context is able to provide superior visual quality to pixel-space obfuscation using the Laplace mechanism.

DP-QIC: A differential privacy scheme based on quasi-identifier classification for big data publication

With the advent of the era of big data, data privacy protection has become a valuable topic in the field of data publication. Unfortunately, traditional methods of privacy protection, k-anonymity, and its extensions are not absolutely secure as an adversary with background knowledge can determine the owner of a record. The emergence of differential privacy provides a reasonable alternative for privacy security, but the existing solutions ignore the correlation between sensitive attributes and other attributes. In this paper, we propose a new differential privacy scheme based on quasi-identifier classification for big data publication (DP-QIC). It is a new data publishing scheme based on the obfuscation of attribute correlation. We innovatively present quasi-identifier classification based on sensitive attributes and the privacy ratio for evaluating the data set vulnerability. DP-QIC achieves data privacy-protecting through four steps: data collection, grouping and shuffling, generalization, merging, and noise adding, which retains the overall statistical characteristics of the data set. Moreover, the exponential mechanism and the Laplace mechanism are integrated to ensure higher flexibility and a stronger level of privacy protection, so DP-QIC can be used for privacy processing of different data groups in future development. Finally, we have compared the performance of our scheme with the other two famous schemes in the industry. Experimental results demonstrate that DP-QIC has obvious advantages in data utility, privacy protection, and processing efficiency.

Correlated tuple data release via differential privacy

Privacy preserving methods supporting for tuple data release have attracted the attention of researchers in multidisciplinary fields. Among the advanced methods, differential privacy (DP), introducing independent Laplace noise, has become an influential privacy mechanism owing to its provable and rigorous privacy guarantee. Nonetheless, in practice, tuple data to be protected are always correlated while independent noise may cause undesirable information disclosure than expected. Recent researches attempt to optimize the sensitivity function of DP with consideration of the correlation strength between data – but have a drawback in a substantial growth of noise level. Therefore, for correlated tuple data release, how to decrease the noise level incurred by correlation strength is yet to be explored. To remedy this problem, this paper exploits the degradation of DP in expected privacy levels for correlated tuple data and proposes a solution to mitigate it. We first demonstrate a filtering attack, presenting a possibility of using the different dependence between original outputs and perturbations to sanitize a certain level of noise to extract individual’s sensitive information. Secondly, we introduce the notion of correlated tuple differential privacy (CTDP) to preserve expected privacy for correlated tuple data and further propose a generalized Laplace mechanism (GLM) to achieve privacy guarantees in CTDP. Then we design a practical iteration mechanism, including an update function, to conduct GLM when facing large scale queries. Finally, experimental evaluation on real-world datasets over multiple fields show that our solution consistently outperforms state-of-the-art mechanisms in data utility while providing the same privacy guarantee as other approaches for correlated tuple data.

Unexpected Information Leakage of Differential Privacy Due to the Linear Property of Queries

Differential privacy is a widely accepted concept of privacy preservation, and the Laplace mechanism is a famous instance of differentially private mechanisms used to deal with numerical data. In this paper, we find that differential privacy does not take the linear property of queries into account, resulting in unexpected information leakage. Specifically, the linear property makes it possible to divide one query into two queries, such as $q(D)=q(D_{1})+q(D_{2})$ if $D=D_{1}\cup D_{2}$ and $D_{1}\cap D_{2}=\emptyset $ . If attackers try to obtain an answer to $q(D)$ , they can not only issue the query $q(D)$ but also issue $q(D_{1})$ and calculate $q(D_{2})$ by themselves as long as they know $D_{2}$ . Through different divisions of one query, attackers can obtain multiple different answers to the same query from differentially private mechanisms. However, from the attackers’ perspective and differentially private mechanisms’ perspective, the total consumed privacy budget is different if divisions are delicately designed. This difference leads to unexpected information leakage because the privacy budget is the key parameter for controlling the amount of information that is legally released from differentially private mechanisms. To demonstrate unexpected information leakage, we present a membership inference attack against the Laplace mechanism. Specifically, under the constraints of differential privacy, we propose a method for obtaining multiple independent identically distributed samples of answers to queries that satisfy the linear property. The proposed method is based on a linear property and some background knowledge of the attackers. When the background knowledge is sufficient, the proposed method can obtain a sufficient number of samples from differentially private mechanisms such that the total consumed privacy budget can be made unreasonably large. Based on the obtained samples, a hypothesis testing method is used to determine whether a target record is in a target dataset.

On Differential Privacy-Based Framework for Enhancing User Data Privacy in Mobile Edge Computing Environment

The potential growth in data mining has an important aspect on security due to the consideration of the data as an asset. The provisioning of protection in a public infrastructure fails to ensure privacy disclosure of an individual’s information. Differential Privacy (DP) is a promising solution for assuring privacy protection by injecting noise using the Laplace mechanism or Exponential mechanism. The access of data by analysts is performed via edge devices. A common problem identified from previous research work is the leakage of privacy at the edge layer and data accessed by unauthorized people. To address the problem, this paper proposes DP-FCNN, that implements Differential Privacy using a Fuzzy Convolution Neural Network (FCNN) with Laplace Mechanism for injecting noise. The processes handled here are data processing and query processing. The dataset is uploaded by the data owner to the data provider, who is responsible for injecting noise and then encrypting with Piccolo encryption before uploading it into the cloud. Based on the uploaded dataset, the data owner constructs a hash index from the extracted key attributes by using the BLAKE2s algorithm for performing hashing. The hash index is fed into the edge server to form a Merkle hash tree due to the data leakage at the edge is eliminated. On the other hand, requests/queries by the data analyst are authenticated by the data provider. The hash tree in the edge server then searches for the corresponding data, extracting it from the cloud and delivers it to the data analyst in an encrypted format. Every authenticated data analyst is provided with a decryption key for retrieving the query result. This is implemented using Java and the results show better efficiency in terms of scalability, processing time and accuracy.

Travel Trajectory Frequent Pattern Mining Based on Differential Privacy Protection

Now, many application services based on location data have brought a lot of convenience to people’s daily life. However, publishing location data may divulge individual sensitive information. Because the location records about location data may be discrete in the database, some existing privacy protection schemes are difficult to protect location data in data mining. In this paper, we propose a travel trajectory data record privacy protection scheme (TMDP) based on differential privacy mechanism, which employs the structure of a trajectory graph model on location database and frequent subgraph mining based on weighted graph. Time series is introduced into the location data; the weighted trajectory model is designed to obtain the travel trajectory graph database. We upgrade the mining of location data to the mining of frequent trajectory graphs, which can discover the relationship of location data from the database and protect location data mined. In particular, to improve the identification efficiency of frequent trajectory graphs, we design a weighted trajectory graph support calculation algorithm based on canonical code and subgraph structure. Moreover, to improve the data utility under the premise of protecting user privacy, we propose double processes of adding noises to the subgraph mining process by the Laplace mechanism and selecting final data by the exponential mechanism. Through formal privacy analysis, we prove that our TMDP framework satisfies ε‐differential privacy. Compared with the other schemes, the experiments show that the data availability of the proposed scheme is higher and the privacy protection of the scheme is effective.