arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.11527cs.CVcs.CR
收藏

基于深度学习的隐写分析中的图像维数不变性研究

A study on the invariance in security whatever the dimension of images for the steganalysis by deep-learning

LIRMM(LIRMM实验室);Univ. Montpellier(蒙彼利埃大学);CNRS(法国国家科学研究中心);Univ. Nîmes(尼姆大学)

Kévin Planolles, Marc Chaumont, Frédéric Comby

摘要:

在本文中,我们研究的性能不变性的卷积神经网络时,面对可变的图像大小的背景下,更“野生隐写分析”。首先,我们提出了两个算法和定义的优良实验协议的数据集具有“相似的难度”和“相似的安全性”。“智能裁剪2”算法允许引入近嵌套图像数据集(NNID),以确保各种数据集之间的“相似难度”,而二分法研究算法允许“相似的安全性”。其次,我们表明,不变性不存在于国家的最先进的架构。我们还表现出行为上的差异,这取决于我们是在比训练图像更大还是更小的图像上进行测试。最后,基于实验,我们建议使用扩张卷积,这导致了一个国家的最先进的架构的改进。

英文摘要:

In this paper, we study the performance invariance of convolutional neural networks when confronted with variable image sizes in the context of a more "wild steganalysis". First, we propose two algorithms and definitions for a fine experimental protocol with datasets owning "similar difficulty" and "similar security". The "smart crop 2" algorithm allows the introduction of the Nearly Nested Image Datasets (NNID) that ensure "a similar difficulty" between various datasets, and a dichotomous research algorithm allows a "similar security". Second, we show that invariance does not exist in state-of-the-art architectures. We also exhibit a difference in behavior depending on whether we test on images larger or smaller than the training images. Finally, based on the experiments, we propose to use the dilated convolution which leads to an improvement of a state-of-the-art architecture.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑