BROWSE
Detail
Conference Paper
Trajectory privacy protection of selective partial area using the GAN model
Cited - time in 
Share 
Share
- Authors
- Yeji Song, Jihwan Shin, Jinhyun Ahn, Taewhi Lee, Dong-Hyuk Im
- Issue Date
- 2021-12
- Citation
- International Conference on Ubiquitous Information Technologies and Applications (CUTE) 2021, pp.1-7
- Language
- English
- Type
- Conference Paper
- Abstract
- Users' privacy is threatened by trajectory data that is rapidly being generated through a location-based services (LBS) environment. Trajectory data is collected from points of interest (POI) data accumulated through social networking services (SNS), and there are several techniques to anonymization the collected trajectory data. We introduce a method of improving privacy protection by reducing the number of points corresponding to the selected POI category in the LSTM-trajGAN model applying the LSTM and GAN structure. We preserve data utility and provide anonymity guarantees (which are trade-off relationship) by selecting a more sensitive POI category.
- KSP Keywords
- Anonymity Guarantees, Data utility, Location-Based Services, Partial area, Points Of Interest, Social Networking Service(SNS), Trade-off, Trajectory Data, Trajectory Privacy Protection