基于迭代对抗样本的JPEG隐写增强算法
Enhancing JPEG Steganography using Iterative Adversarial Examples
摘要：
基于卷积神经网络（CNN）的方法与传统的基于手工特征的方法相比，显著提高了图像隐写分析的性能。然而，许多现有的计算机视觉的文献指出，这些有效的基于CNN的方法可以很容易地被欺骗的敌对的例子。在本文中，我们提出了一种新的隐写框架的基础上对抗性的例子在迭代的方式。该框架首先从现有的嵌入成本开始，如J-UNIWARD在这项工作中，然后基于来自一系列隐写分析网络的对抗性示例迭代更新成本，直到获得满意的结果。我们仔细分析了两个重要的因素，将影响所提出的框架的安全性能，即具有较大幅度的选择梯度的百分比和对抗强度修改嵌入成本。在GFR、SCA-GFR和SRNet三种现代隐写分析模型上的实验结果表明，该框架对提高JPEG隐写的安全性能具有很好的应用前景。
英文摘要：
Convolutional Neural Networks (CNN) based methods have significantly improved the performance of image steganalysis compared with conventional ones based on hand-crafted features. However, many existing literatures on computer vision have pointed out that those effective CNN-based methods can be easily fooled by adversarial examples. In this paper, we propose a novel steganography framework based on adversarial example in an iterative manner. The proposed framework first starts from an existing embedding cost, such as J-UNIWARD in this work, and then updates the cost iteratively based on adversarial examples derived from a series of steganalytic networks until achieving satisfactory results. We carefully analyze two important factors that would affect the security performance of the proposed framework, i.e. the percentage of selected gradients with larger amplitude and the adversarial intensity to modify embedding cost. The experimental results evaluated on three modern steganalytic models, including GFR, SCA-GFR and SRNet, show that the proposed framework is very promising to enhance the security performances of JPEG steganography.
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。
