A Fusion-Denoising Attack on InstaHide with Data Augmentation
Authors: Xinjian Luo, Xiaokui Xiao, Yuncheng Wu, Juncheng Liu, Beng Chin Ooi1899-1907
AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments demonstrate the effectiveness of the proposed attack in comparison to Carlini et al. s attack. The results demonstrate the superior performance of the proposed scheme to (Carlini et al. 2020). |
| Researcher Affiliation | Academia | National University of Singapore {xinjluo, xiaoxk, wuyc, juncheng, ooibc}@comp.nus.edu.sg |
| Pseudocode | No | The paper describes the proposed methods but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement about releasing its own source code for the described methodology, nor does it provide a link to a code repository. |
| Open Datasets | Yes | We use CIFAR10 (Krizhevsky and Hinton 2009), CIFAR100 (Krizhevsky and Hinton 2009), STL10 (Coates, Ng, and Lee 2011) and Celeb Faces (CELEBA) (Liu et al. 2015) as the training and testing datasets. |
| Dataset Splits | No | The paper mentions training and testing datasets but does not explicitly provide details about training/validation/test splits, such as percentages, sample counts, or cross-validation methods. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as GPU models, CPU models, or memory used for running the experiments. |
| Software Dependencies | No | The paper mentions software components like 'Res Net-28', 'RNAN', and 'Adam', but does not provide specific version numbers for these or any other ancillary software dependencies. |
| Experiment Setup | Yes | The λMSSIM in Eq. 4 is empirically set to 0.7. The Insta Hide parameterized with k = 6 is employed unless otherwise specified. More setting details are reported in the ar Xiv version. |