UPSET和ANGRI:突破性的高性能图像分类器
UPSET and ANGRI : Breaking High Performance Image Classifiers
摘要:
在本文中,有针对性的愚弄高性能的图像分类器实现了开发两种新的攻击方法。第一种方法生成目标类的通用扰动,第二种方法生成图像特定的扰动。在MNIST和CIFAR10数据集上进行了大量的实验,以提供有关所提出的算法的见解,并显示其有效性。
英文摘要:
In this paper, targeted fooling of high performance image classifiers is achieved by developing two novel attack methods. The first method generates universal perturbations for target classes and the second generates image specific perturbations. Extensive experiments are conducted on MNIST and CIFAR10 datasets to provide insights about the proposed algorithms and show their effectiveness.
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。