DP-WHERE: Differentially private modeling of human mobility

By Darakhshan J. Mir, Sibren Isaacman, Ramón Cáceres, Margaret Martonosi, Rebecca N. Wright. 2013

147 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Transportation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. A. K. Qin
2. Claude Castelluccia
3. Hongxia Jin
4. Vincent D. Blondel
5. Gianni Barlacchi
6. Rui Chen
7. Haoran Li
8. Luca Pappalardo

In Computer Networks and Communications

1. Claude Castelluccia
2. Hongxia Jin
3. Vincent D. Blondel
4. Gergely Ács
5. Shiva Prasad Kasiviswanathan
6. Olaf Sporns
7. Karim Eldefrawy

In Transportation

1. Vincent D. Blondel
2. Laura Ferrari
3. Francesco Calabrese
4. A. K. Qin
5. Gianni Barlacchi
6. Luca Pappalardo
7. Massimiliano Luca
8. Bruno Lepri

Citations in the corpus

• Advanced Probabilistic Couplings for Differential Privacy (2016, neutral): “Other tools implement algorithms targeting specific applications like: location data [35], genomic data [27, 47], mobility data [37], and browser error reports [26].”
• Machine Learning for Synthetic Data Generation: a Review (2023, unknown): “…deep neural network architectures as background knowledge, including multiple layer perception (MLP) in Section III-A, convolutional neural network (CNN) in Section III-B, recurrent neural network (RNN) in Section III-C, graph neural network (GNN) in Section III-D and transformer in Section III-E.”
• Study : Privacy Preserving Release of Spatio-temporal Density in Paris (2014, background): “This mapping between CDRs and IRIS cells influences utility and is not considered in [23].”
• A Survey on Deep Learning for Human Mobility (2020, background): “Furthermore, generative models are a viable solution to protect geo-privacy of trajectory data [62, 124, 144]: While disclosing real data requires a hard-to-control tradeoff between uncertainty and utility, synthetic records that preserve statistical properties may achieve in multiple tasks comparab”
• Urban Sensing Using Mobile Phone Network Data: A Survey of Research (2014, methodology): “Very recently, (Mir et al., 2013) have also proposed a method, validated against billions of location samples from a real telecommunication network, to generate synthetic Call Detail Records to capture the mobility patterns of real metropolitan populations while preserving privacy.”
• Private spatial data aggregation in the local setting (2016, background): “Mir et al. [11] present a differentially private approach to model human mobility patterns based on call-detail-records (CDRs).”