More Like this

1. Differentially-Private Next-Location Prediction with Neural Networks

   Ahuja, Ritesh; Ghinita, Gabriel; Shahabi, Cyrus (March 2020, Advances in database technology)

   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research efforts focused on privacy-preserving next-location prediction, but they have serious limitations: some use outdated privacy models (e.g., k-anonymity), while others employ learning models with limited expressivity (e.g., matrix factorization).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
2. Differentially-Private Next-Location Prediction with Neural Networks

   Ahuja, Ritesh; Ghinita, Gabriel; Shahabi, Cyrus (March 2020, Advances in database technology)

   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
3. Mobile Application Privacy Risk Assessments from User-authored Scenarios

   https://doi.org/10.1109/RE57278.2023.00012  

   Huang, Tianjian; Kaulagi, Vaishnavi; Hosseini, Mitra Bokaei; Breaux, Travis (September 2023, IEEE)

   Mobile applications (apps) provide users valuable benefits at the risk of exposing users to privacy harms. Improving privacy in mobile apps faces several challenges, in particular, that many apps are developed by low resourced software development teams, such as end-user programmers or in startups. In addition, privacy risks are primarily known to users, which can make it difficult for developers to prioritize privacy for sensitive data. In this paper, we introduce a novel, lightweight method that allows app developers to elicit scenarios and privacy risk scores from users directly using only an app screenshot. The technique relies on named entity recognition (NER) to identify information types in user-authored scenarios, which are then fed in real-time to a privacy risk survey that users complete. The best-performing NER model predicts information types with a weighted average precision of 0.70 and recall of 0.72, after post-processing to remove false positives. The model was trained on a labeled 300-scenario corpus, and evaluated in an end-to-end evaluation using an additional 203 scenarios yielding 2,338 user-provided privacy risk scores. Finally, we discuss how developers can use the risk scores to prioritize, select and apply privacy design strategies in the context of four user-authored scenarios. 

   more » « less
4. Characterizing Location-based Mobile Tracking in Mobile Ad Networks

   https://doi.org/10.1109/CNS.2019.8802632  

   Hu, Boyang; Lin, Qicheng; Zheng, Yao; Yan, Qiben; Troglia, Matthew; Wang, Qingyang (March 2019, IEEE CNS 2019)

   Mobile apps nowadays are often packaged with third-party ad libraries to monetize user data. Many mobile ad networks exploit these mobile apps to extract sensitive real-time geographical data about the users for location-based targeted advertising. However, the massive collection of sensitive information by the ad networks has raised serious privacy concerns. Unfortunately, the extent and granularity of private data collection of the location-based ad networks remain obscure. In this work, we present a mobile tracking measurement study to characterize the severity and significance of location-based private data collection in mobile ad networks, by using an automated fine-grained data collection instrument running across different geographical areas. We perform extensive threat assessments for different ad networks using 1,100 popular apps running across 10 different cities. This study discovers that the number of location-based ads tend to be positively correlated with the population density of locations, ad networks' data collection behaviors differ across different locations, and most ad networks are capable of collecting precise location data. Detailed analysis further reveals the significant impact of geolocation on the tracking behavior of targeted ads, and a noteworthy security concern for advertising organizations to aggregate different types of private user data across multiple apps for a better targeted ad experience. 

   more » « less
5. BehaVR: User Identification Based on VR Sensor Data

   https://doi.org/10.56553/popets-2025-0022  

   Jarin, Ismat; Duan, Yu; Trimananda, Rahmadi; Cui, Hao; Elmalaki, Salma; Markopoulou, Athina (January 2025, Proceedings on Privacy Enhancing Technologies)

   Virtual reality (VR) platforms enable a wide range of applications, however, pose unique privacy risks. In particular, VR devices are equipped with a rich set of sensors that collect personal and sensitive information (e.g., body motion, eye gaze, hand joints, and facial expression). The data from these newly available sensors can be used to uniquely identify a user, even in the absence of explicit identifiers. In this paper, we seek to understand the extent to which a user can be identified based solely on VR sensor data, within and across real-world apps from diverse genres. We consider adversaries with capabilities that range from observing APIs available within a single app (app adversary) to observing all or selected sensor measurements across multiple apps on the VR device (device adversary). To that end, we introduce BehaVR, a framework for collecting and analyzing data from all sensor groups collected by multiple apps running on a VR device. We use BehaVR to collect data from real users that interact with 20 popular real-world apps. We use that data to build machine learning models for user identification within and across apps, with features extracted from available sensor data. We show that these models can identify users with an accuracy of up to 100%, and we reveal the most important features and sensor groups, depending on the functionality of the app and the adversary. To the best of our knowledge, BehaVR is the first to analyze user identification in VR comprehensively, i.e., considering all sensor measurements available on consumer VR devices, collected by multiple real-world, as opposed to custom-made, apps. 

   more » « less