A Differentially Private Multi-Output Deep Generative Networks Approach For Activity Diary Synthesis
This work addresses the problem of synthesizing realistic travel activity data while protecting the privacy of survey participants, which is important for urban planners and transportation researchers.
This paper develops a privacy-by-design generative model using deep learning to synthesize activity diaries of a travel population. The model successfully simulates activity diaries, including structured socio-economic features and sequential tour activities, while guaranteeing differential privacy.
In this work, we develop a privacy-by-design generative model for synthesizing the activity diary of the travel population using state-of-art deep learning approaches. This proposed approach extends literature on population synthesis by contributing novel deep learning to the development and application of synthetic travel data while guaranteeing privacy protection for members of the sample population on which the synthetic populations are based. First, we show a complete de-generalization of activity diaries to simulate the socioeconomic features and longitudinal sequences of geographically and temporally explicit activities. Second, we introduce a differential privacy approach to control the level of resolution disclosing the uniqueness of survey participants. Finally, we experiment using the Generative Adversarial Networks (GANs). We evaluate the statistical distributions, pairwise correlations and measure the level of privacy guaranteed on simulated datasets for varying noise. The results of the model show successes in simulating activity diaries composed of multiple outputs including structured socio-economic features and sequential tour activities in a differentially private manner.