Monga Vishal, Evans Brian L
Xerox Innovation Group, El Segundo, CA 90245, USA.
IEEE Trans Image Process. 2006 Nov;15(11):3452-65. doi: 10.1109/tip.2006.881948.
We propose an image hashing paradigm using visually significant feature points. The feature points should be largely invariant under perceptually insignificant distortions. To satisfy this, we propose an iterative feature detector to extract significant geometry preserving feature points. We apply probabilistic quantization on the derived features to introduce randomness, which, in turn, reduces vulnerability to adversarial attacks. The proposed hash algorithm withstands standard benchmark (e.g., Stirmark) attacks, including compression, geometric distortions of scaling and small-angle rotation, and common signal-processing operations. Content changing (malicious) manipulations of image data are also accurately detected. Detailed statistical analysis in the form of receiver operating characteristic (ROC) curves is presented and reveals the success of the proposed scheme in achieving perceptual robustness while avoiding misclassification.
我们提出了一种使用视觉上显著特征点的图像哈希范式。这些特征点在感知上不显著的失真下应基本保持不变。为满足这一要求，我们提出一种迭代特征检测器来提取显著的几何形状保留特征点。我们对导出的特征应用概率量化以引入随机性，这反过来又降低了对抗攻击的脆弱性。所提出的哈希算法能够抵御标准基准（如Stirmark）攻击，包括压缩、缩放和小角度旋转的几何失真以及常见的信号处理操作。图像数据的内容更改（恶意）操作也能被准确检测到。以接收者操作特征（ROC）曲线形式进行的详细统计分析表明，所提出的方案在实现感知鲁棒性同时避免误分类方面取得了成功。
