Secrets Everywhere: Auditing Memorization in Mobility Prediction Models

• URL: http://arxiv.org/abs/2608.02052v1
• Date: Mon, 03 Aug 2026 10:47:56 GMT
• Title: Secrets Everywhere: Auditing Memorization in Mobility Prediction Models
• Abstract summary: We conduct the first systematic audit of memorization in mobility prediction models.<n>Key challenges include the lack of a randomness space, the multi-scale structure of trajectories, and user-specific behavioral diversity.<n>Our findings call for mandatory privacy auditing in mobility prediction models.
• Score: 3.476159749530156
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Human mobility prediction models, which forecast the next location in a user's trajectory, are increasingly deployed in urban analytics, navigation, and personalized services. Yet, little is known about their potential to memorize and expose sensitive user trajectories from training data. While memorization has been extensively studied in language models, mobility prediction poses unique challenges: training sequences encode human behavior at various spatial and temporal scales, creating privacy risks at different granularities. In this paper, we conduct the first systematic audit of memorization in mobility prediction models. While prior work has shown that privacy leaks can arise from such models, we systematically assess and quantify memorization risks at scale. We identify key challenges, including the lack of a randomness space, the multi-scale structure of trajectories, and user-specific behavioral diversity. To address these challenges, we introduce a framework to quantify mobility memorization at different levels of granularity: individual locations, anchor pairs, and subtrajectory segments. We also develop user-grounded reference sets to assess how likely a model is to prefer training data over realistic alternatives. Our evaluation across multiple models and datasets reveals pervasive memorization patterns that correlate with user regularity and increase the risk of data extraction at inference time. Our findings call for mandatory privacy auditing in mobility prediction models.

Related papers

• BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces [53.55407626944686]
  textscBehaviorBench is a benchmark for evaluating personalized decision modeling from real-world behavioral traces.<n>textscBehaviorBench reconstructs wallet-level decision histories from observed public prediction-market and on-chain records.<n>Across 2,000 evaluation wallets, the benchmark contains 141,445 Belief instances and 1,485,972 Trade instances.
  arXiv  Detail & Related papers  (2026-06-01T19:04:36Z)
• Training Machine Learning Models on Human Spatio-temporal Mobility Data: An Experimental Study [Experiment Paper] [0.5382679710017696]
  Individual-level human mobility prediction has emerged as a significant topic of research with applications in infectious disease monitoring, child, and elderly care.<n>We focus on an underexplored problem in human mobility prediction: determining the best practices to train a machine learning model.<n>We show that explicitly including semantic information can help the model better understand individual patterns of life and improve predictions.
  arXiv  Detail & Related papers  (2025-08-18T17:49:10Z)
• Into the Unknown: Applying Inductive Spatial-Semantic Location Embeddings for Predicting Individuals' Mobility Beyond Visited Places [3.131843231859519]
  CaLLiPer is a representation learning framework that fuses spatial coordinates and semantic features of points of interest through contrastive learning.<n>Our findings highlight the potential of multimodal, inductive location embeddings to advance the capabilities of human mobility prediction systems.
  arXiv  Detail & Related papers  (2025-06-17T00:00:09Z)
• New Emerged Security and Privacy of Pre-trained Model: a Survey and Outlook [54.24701201956833]
  Security and privacy issues have undermined users' confidence in pre-trained models. Current literature lacks a clear taxonomy of emerging attacks and defenses for pre-trained models. This taxonomy categorizes attacks and defenses into No-Change, Input-Change, and Model-Change approaches.
  arXiv  Detail & Related papers  (2024-11-12T10:15:33Z)
• Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models [112.48136829374741]
  In this paper, we unveil a new vulnerability: the privacy backdoor attack. When a victim fine-tunes a backdoored model, their training data will be leaked at a significantly higher rate than if they had fine-tuned a typical model. Our findings highlight a critical privacy concern within the machine learning community and call for a reevaluation of safety protocols in the use of open-source pre-trained models.
  arXiv  Detail & Related papers  (2024-04-01T16:50:54Z)
• JRDB-Traj: A Dataset and Benchmark for Trajectory Forecasting in Crowds [79.00975648564483]
  Trajectory forecasting models, employed in fields such as robotics, autonomous vehicles, and navigation, face challenges in real-world scenarios. This dataset provides comprehensive data, including the locations of all agents, scene images, and point clouds, all from the robot's perspective. The objective is to predict the future positions of agents relative to the robot using raw sensory input data.
  arXiv  Detail & Related papers  (2023-11-05T18:59:31Z)
• Survey of Federated Learning Models for Spatial-Temporal Mobility Applications [9.896508514316812]
  Federated learning (FL) can serve as an ideal candidate for training spatial temporal models. There are unique challenges involved with transitioning existing spatial temporal models to decentralized learning.
  arXiv  Detail & Related papers  (2023-05-09T08:26:48Z)
• Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck [77.37409441129995]
  In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition. We consider an adversarial threat model under a mutual information constraint to cover a wider class of perturbations in training. We propose an autoencoder-based training to implement the objective, as well as practical encoder designs to facilitate the proposed hybrid discriminative-generative training.
  arXiv  Detail & Related papers  (2023-03-24T16:03:21Z)
• Context-aware multi-head self-attentional neural network model for next location prediction [19.640761373993417]
  We utilize a multi-head self-attentional (A) neural network that learns location patterns from historical location visits. We demonstrate that proposed the model outperforms other state-of-the-art prediction models. We believe that the proposed model is vital for context-aware mobility prediction.
  arXiv  Detail & Related papers  (2022-12-04T23:40:14Z)
• Synthetic Model Combination: An Instance-wise Approach to Unsupervised Ensemble Learning [92.89846887298852]
  Consider making a prediction over new test data without any opportunity to learn from a training set of labelled data. Give access to a set of expert models and their predictions alongside some limited information about the dataset used to train them.
  arXiv  Detail & Related papers  (2022-10-11T10:20:31Z)
• Leveraging Adversarial Examples to Quantify Membership Information Leakage [30.55736840515317]
  We develop a novel approach to address the problem of membership inference in pattern recognition models. We argue that this quantity reflects the likelihood of belonging to the training data. Our method performs comparable or even outperforms state-of-the-art strategies.
  arXiv  Detail & Related papers  (2022-03-17T19:09:38Z)
• Diverse Complexity Measures for Dataset Curation in Self-driving [80.55417232642124]
  We propose a new data selection method that exploits a diverse set of criteria that quantize interestingness of traffic scenes. Our experiments show that the proposed curation pipeline is able to select datasets that lead to better generalization and higher performance.
  arXiv  Detail & Related papers  (2021-01-16T23:45:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.