The emergence of mobile apps (e.g., location-based services, geo-social networks, ride-sharing) led to the collection of vast amounts of trajectory data that greatly benefit the understanding of individual mobility. One problem of particular interest is next-location prediction, which facilitates location-based advertising, point-of-interest recommendation, traffic optimization,etc. However, using individual trajectories to build prediction models introduces serious privacy concerns, since exact whereabouts of users can disclose sensitive information such as their health status or lifestyle choices. Several research efforts focused on privacy-preserving next-location prediction, but they have serious limitations: some use outdated privacy models (e.g., k-anonymity), while others employ learning models with limited expressivity (e.g., matrix factorization). More recent approaches(e.g., DP-SGD) integrate the powerful differential privacy model with neural networks, but they provide only generic and difficult-to-tune methods that do not perform well on location data, which is inherently skewed and sparse.We propose a technique that builds upon DP-SGD, but adapts it for the requirements of next-location prediction. We focus on user-level privacy, a strong privacy guarantee that protects users regardless of how much data they contribute. Central to our approach is the use of the skip-gram model, and its negative sampling technique. Our work is the first to propose differentially-private learning with skip-grams. In addition, we devise data grouping techniques within the skip-gram framework that pool together trajectories from multiple users in order to accelerate learning and improve model accuracy. Experiments conducted on real datasets demonstrate that our approach significantly boosts prediction accuracy compared to existing DP-SGD techniques.
more »
« less
Structured Sparsity Model Based Trajectory Tracking Using Private Location Data Release
Mobile devices have been an integral part of our everyday lives. Users' increasing interaction with mobile devices brings in significant concerns on various types of potential privacy leakage, among which location privacy draws the most attention. Specifically, mobile users' trajectories constructed by location data may be captured by adversaries to infer sensitive information. In previous studies, differential privacy has been utilized to protect published trajectory data with rigorous privacy guarantee. Strong protection provided by differential privacy distorts the original locations or trajectories using stochastic noise to avoid privacy leakage. In this paper, we propose a novel location inference attack framework, iTracker, which simultaneously recovers multiple trajectories from differentially private trajectory data using the structured sparsity model. Compared with the traditional recovery methods based on single trajectory prediction, iTracker, which takes advantage of the correlation among trajectories discovered by the structured sparsity model, is more effective in recovering multiple private trajectories simultaneously. iTracker successfully attacks the existing privacy protection mechanisms based on differential privacy. We theoretically demonstrate the near-linear runtime of iTracker, and the experimental results using two real-world datasets show that iTracker outperforms existing recovery algorithms in recovering multiple trajectories.
more »
« less
- Award ID(s):
- 1954376
- NSF-PAR ID:
- 10223469
- Date Published:
- Journal Name:
- IEEE Transactions on Dependable and Secure Computing
- ISSN:
- 1545-5971
- Page Range / eLocation ID:
- 1 to 1
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The emergence of mobile apps (e.g., location-based services,geo-social networks, ride-sharing) led to the collection of vast amounts of trajectory data that greatly benefit the understanding of individual mobility. One problem of particular interest is next-location prediction, which facilitates location-based advertising, point-of-interest recommendation, traffic optimization,etc. However, using individual trajectories to build prediction models introduces serious privacy concerns, since exact whereabouts of users can disclose sensitive information such as their health status or lifestyle choices. Several research efforts focused on privacy-preserving next-location prediction, but they have serious limitations: some use outdated privacy models (e.g., k-anonymity), while others employ learning models with limited expressivity (e.g., matrix factorization). More recent approaches(e.g., DP-SGD) integrate the powerful differential privacy model with neural networks, but they provide only generic and difficult-to-tune methods that do not perform well on location data, which is inherently skewed and sparse.We propose a technique that builds upon DP-SGD, but adapts it for the requirements of next-location prediction. We focus on user-level privacy, a strong privacy guarantee that protects users regardless of how much data they contribute. Central toour approach is the use of the skip-gram model, and its negative sampling technique. Our work is the first to propose differentially-private learning with skip-grams. In addition, we devise data grouping techniques within the skip-gram framework that pool together trajectories from multiple users in order to acceleratelearning and improve model accuracy. Experiments conducted on real datasets demonstrate that our approach significantly boosts prediction accuracy compared to existing DP-SGD techniques.more » « less
-
Recently, the ubiquity of mobile devices leads to an increasing demand of public network services, e.g., WiFi hot spots. As a part of this trend, modern transportation systems are equipped with public WiFi devices to provide Internet access for passengers as people spend a large amount of time on public transportation in their daily life. However, one of the key issues in public WiFi spots is the privacy concern due to its open access nature. Existing works either studied location privacy risk in human traces or privacy leakage in private networks such as cellular networks based on the data from cellular carriers. To the best of our knowledge, none of these work has been focused on bus WiFi privacy based on large-scale real-world data. In this paper, to explore the privacy risk in bus WiFi systems, we focus on two key questions how likely bus WiFi users can be uniquely re-identified if partial usage information is leaked and how we can protect users from the leaked information. To understand the above questions, we conduct a case study in a large-scale bus WiFi system, which contains 20 million connection records and 78 million location records from 770 thousand bus WiFi users during a two-month period. Technically, we design two models for our uniqueness analyses and protection, i.e., a PB-FIND model to identify the probability a user can be uniquely re-identified from leaked information; a PB-HIDE model to protect users from potentially leaked information. Specifically, we systematically measure the user uniqueness on users' finger traces (i.e., connection URL and domain), foot traces (i.e., locations), and hybrid traces (i.e., both finger and foot traces). Our measurement results reveal (i) 97.8% users can be uniquely re-identified by 4 random domain records of their finger traces and 96.2% users can be uniquely re-identified by 5 random locations on buses; (ii) 98.1% users can be uniquely re-identified by only 2 random records if both their connection records and locations are leaked to attackers. Moreover, the evaluation results show our PB-HIDE algorithm protects more than 95% users from the potentially leaked information by inserting only 1.5% synthetic records in the original dataset to preserve their data utility.more » « less
-
We consider the problem of predicting cellular network performance (signal maps) from measurements collected by several mobile devices. We formulate the problem within the online federated learning framework: (i) federated learning (FL) enables users to collaboratively train a model, while keeping their training data on their devices; (ii) measurements are collected as users move around over time and are used for local training in an online fashion. We consider an honest-but-curious server, who observes the updates from target users participating in FL and infers their location using a deep leakage from gradients (DLG) type of attack, originally developed to reconstruct training data of DNN image classifiers. We make the key observation that a DLG attack, applied to our setting, infers the average location of a batch of local data, and can thus be used to reconstruct the target users' trajectory at a coarse granularity. We build on this observation to protect location privacy, in our setting, by revisiting and designing mechanisms within the federated learning framework including: tuning the FL parameters for averaging, curating local batches so as to mislead the DLG attacker, and aggregating across multiple users with different trajectories. We evaluate the performance of our algorithms through both analysis and simulation based on real-world mobile datasets, and we show that they achieve a good privacy-utility tradeoff.more » « less
-
more » « less
Abstract Lifestyle recovery captures the collective effects of population activities as well as the restoration of infrastructure and business services. This study uses a novel approach to leverage privacy-enhanced location intelligence data, which is anonymized and aggregated, to characterize distinctive lifestyle patterns and to unveil recovery trajectories after 2017 Hurricane Harvey in Harris County, Texas (USA). The analysis integrates multiple data sources to record the number of visits from home census block groups (CBGs) to different points of interest (POIs) in the county during the baseline and disaster periods. For the methodology, the research utilizes unsupervised machine learning and ANOVA statistical testing to characterize the recovery of lifestyles using privacy-enhanced location intelligence data. First, primary clustering using k-means characterized four distinct essential and non-essential lifestyle patterns. For each primary lifestyle cluster, the secondary clustering characterized the impact of the hurricane into four possible recovery trajectories based on the severity of maximum disruption and duration of recovery. The findings further reveal multiple recovery trajectories and durations within each lifestyle cluster, which imply differential recovery rates among similar lifestyles and different demographic groups. The impact of flooding on lifestyle recovery extends beyond the flooded regions, as 59% of CBGs with extreme recovery durations did not have at least 1% of direct flooding impacts. The findings offer a twofold theoretical significance: (1) lifestyle recovery is a critical milestone that needs to be examined, quantified, and monitored in the aftermath of disasters; (2) spatial structures of cities formed by human mobility and distribution of facilities extend the spatial reach of flood impacts on population lifestyles. These provide novel data-driven insights for public officials and emergency managers to examine, measure, and monitor a critical milestone in community recovery trajectory based on the return of lifestyles to normalcy.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1109/tdsc.2020.2972334
