paper-with-me

Papers

Generative Adversarial Privacy

2018-07-13 · ICLR 2019 5 · Chong Huang, Peter Kairouz, Xiao Chen, Lalitha Sankar, Ram Rajagopal

We present a data-driven framework called generative adversarial privacy (GAP). Inspired by recent advancements in generative adversarial networks (GANs), GAP allows the data holder to learn the privatization mechanism directly from the data. Under GAP, finding the optimal privacy mechanism is formulated as a constrained minimax game between a privatizer and an adversary. We show that for appropriately chosen adversarial loss functions, GAP provides privacy guarantees against strong information-theoretic adversaries. We also evaluate GAP's performance on the GENKI face database.

📄 PDF Abstract BibTeX arXiv:1807.05306

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Context-Aware Generative Adversarial Privacy

2017-10-26 · Chong Huang, Peter Kairouz, Xiao Chen, Lalitha Sankar 외

Preserving the utility of published datasets while simultaneously providing provable privacy guarantees is a well-known challenge. On the one hand, context-free privacy solutions, such as differential privacy, provide st…

Privacy Evaluation of Generative Models for Trajectory Generation

2026-05-14 · Stavros Bouras, Ioannis Kontopoulos, Chiara Pugliese, Francesco Lettich 외 arxiv

Trajectory data is fundamental to modern urban intelligence, yet its sensitivity raises significant privacy concerns. Generative models such as Generative Adversarial Networks, Variational Autoencoders, and Diffusion Mod…

Trajectory Modeling

PPGAN: Privacy-preserving Generative Adversarial Network

2019-10-04 · Yi Liu, Jialiang Peng, James J. Q. Yu, Yi Wu

Generative Adversarial Network (GAN) and its variants serve as a perfect representation of the data generation model, providing researchers with a large amount of high-quality generated data. They illustrate a promising …

Generative Adversarial NetworkPrivacy Preserving

imdpGAN: Generating Private and Specific Data with Generative Adversarial Networks

2020-09-29 · Saurabh Gupta, Arun Balaji Buduru, Ponnurangam Kumaraguru

Generative Adversarial Network (GAN) and its variants have shown promising results in generating synthetic data. However, the issues with GANs are: (i) the learning happens around the training samples and the model often…

Binary ClassificationGenerative Adversarial NetworkSpecificity

Generative Adversarial Models for Learning Private and Fair Representations

2019-05-01 · ICLR 2019 5 · Chong Huang, Xiao Chen, Peter Kairouz, Lalitha Sankar 외

We present Generative Adversarial Privacy and Fairness (GAPF), a data-driven framework for learning private and fair representations of the data. GAPF leverages recent advances in adversarial learning to allow a data hol…

Fairness