ST-DPGAN: A Privacy-preserving Framework for Spatiotemporal Data Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916275941277696 |
|---|---|
| author | Shao, Wei Zhu, Rongyi Yang, Cai Thapa, Chandra Ahmed, Muhammad Ejaz Camtepe, Seyit Zhang, Rui Kim, DuYong Menouar, Hamid Salim, Flora D. |
| author_facet | Shao, Wei Zhu, Rongyi Yang, Cai Thapa, Chandra Ahmed, Muhammad Ejaz Camtepe, Seyit Zhang, Rui Kim, DuYong Menouar, Hamid Salim, Flora D. |
| contents | Spatiotemporal data is prevalent in a wide range of edge devices, such as those used in personal communication and financial transactions. Recent advancements have sparked a growing interest in integrating spatiotemporal analysis with large-scale language models. However, spatiotemporal data often contains sensitive information, making it unsuitable for open third-party access. To address this challenge, we propose a Graph-GAN-based model for generating privacy-protected spatiotemporal data. Our approach incorporates spatial and temporal attention blocks in the discriminator and a spatiotemporal deconvolution structure in the generator. These enhancements enable efficient training under Gaussian noise to achieve differential privacy. Extensive experiments conducted on three real-world spatiotemporal datasets validate the efficacy of our model. Our method provides a privacy guarantee while maintaining the data utility. The prediction model trained on our generated data maintains a competitive performance compared to the model trained on the original data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_03404 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ST-DPGAN: A Privacy-preserving Framework for Spatiotemporal Data Generation Shao, Wei Zhu, Rongyi Yang, Cai Thapa, Chandra Ahmed, Muhammad Ejaz Camtepe, Seyit Zhang, Rui Kim, DuYong Menouar, Hamid Salim, Flora D. Machine Learning Artificial Intelligence Cryptography and Security Spatiotemporal data is prevalent in a wide range of edge devices, such as those used in personal communication and financial transactions. Recent advancements have sparked a growing interest in integrating spatiotemporal analysis with large-scale language models. However, spatiotemporal data often contains sensitive information, making it unsuitable for open third-party access. To address this challenge, we propose a Graph-GAN-based model for generating privacy-protected spatiotemporal data. Our approach incorporates spatial and temporal attention blocks in the discriminator and a spatiotemporal deconvolution structure in the generator. These enhancements enable efficient training under Gaussian noise to achieve differential privacy. Extensive experiments conducted on three real-world spatiotemporal datasets validate the efficacy of our model. Our method provides a privacy guarantee while maintaining the data utility. The prediction model trained on our generated data maintains a competitive performance compared to the model trained on the original data. |
| title | ST-DPGAN: A Privacy-preserving Framework for Spatiotemporal Data Generation |
| topic | Machine Learning Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2406.03404 |