Wasserstein Differential Privacy
Authors: Chengyi Yang, Jiayin Qi, Aimin Zhou
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on basic mechanisms, compositions and deep learning show that the privacy budgets obtained by Wasserstein accountant are relatively stable and less influenced by order. Moreover, the overestimation on privacy budgets can be effectively alleviated. The code is available at https://github.com/Hifipsysta/WDP. |
| Researcher Affiliation | Academia | 1Shanghai Institute of AI for Education, School of Computer Science and Technology, and Key Laboratory of MEA (Ministry of Education), East China Normal University 2Cyberspace Institute of Advanced Technology, Guangzhou University |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. It primarily presents mathematical definitions, propositions, and theorems. |
| Open Source Code | Yes | The code is available at https://github.com/Hifipsysta/WDP. |
| Open Datasets | Yes | train a convolutional neural network (CNN)... on four baseline datasets including MNIST (Lecun et al. 1998), CIFAR-10 (Krizhevsky and Hinton 2009), SVHN (Netzer et al. 2011) and Fashion-MNIST (Xiao, Rasul, and Vollgraf 2017). |
| Dataset Splits | No | The paper does not provide specific dataset split information (exact percentages, sample counts, or explicit detailed splitting methodology) for training, validation, and testing. It mentions using baseline datasets but not their specific splits for reproduction beyond the common understanding of these datasets. |
| Hardware Specification | Yes | All the experiments were performed on a single machine with Ubuntu 18.04, 40 Intel(R) Xeon(R) Silver 4210R CPUs @ 2.40GHz, and two NVIDIA Quadro RTX 8000 GPUs. |
| Software Dependencies | No | The paper mentions "Ubuntu 18.04" but does not provide specific version numbers for other key software components, libraries, or frameworks used in the experiments. |
| Experiment Setup | Yes | We set the scale parameters of Laplace mechanism and Gaussian mechanism as 1, 2, 3 and 5 respectively. The order µ of WDP is allowed to varies from 1 to 10, and so is the order of RDP... The hyper-parameter σ remains unchanged after being set as 0.2, and the threshold of gradient clipping C is set to {0.05, 0.50, 0.75, 0.99}-quantiles of gradient norm in turns. |