迈向防御性字母设计
Toward Defensive Letter Design
AI总结：
本文提出通过控制字母外观来增强其对对抗性攻击的防御性，利用I-FGSM测量防御性并构建回归模型估计，同时提出基于GAN的两步方法生成高防御性字符图像。
摘要：
针对对抗性攻击的主要防御方法旨在仅控制图像分类器使其更具鲁棒性，而不关心图像中的视觉对象（如熊猫和汽车）。这意味着视觉对象本身无法采取任何防御行动，它们仍然容易受到对抗性攻击。相比之下，字母是人工符号，我们可以在不失去可读性的前提下自由控制其外观。换言之，我们可以使字母对攻击更具防御性。本文提出了与字母图像对抗脆弱性相关的三个研究问题：（1）字母对对抗性攻击的防御性如何？（2）我们能否在攻击前估计给定字母图像的防御性？（3）我们能否控制字母图像使其对对抗性攻击更具防御性？为回答第一和第二个问题，我们采用迭代快速梯度符号法（I-FGSM）测量字母的防御性，然后构建一个深度回归模型来估计每个字母图像的防御性。我们还提出了一种基于生成对抗网络（GAN）的两步方法，用于生成具有更高防御性的字符图像，从而解决第三个研究问题。
英文摘要：
A major approach for defending against adversarial attacks aims at controlling only image classifiers to be more resilient, and it does not care about visual objects, such as pandas and cars, in images. This means that visual objects themselves cannot take any defensive actions, and they are still vulnerable to adversarial attacks. In contrast, letters are artificial symbols, and we can freely control their appearance unless losing their readability. In other words, we can make the letters more defensive to the attacks. This paper poses three research questions related to the adversarial vulnerability of letter images: (1) How defensive are the letters against adversarial attacks? (2) Can we estimate how defensive a given letter image is before attacks? (3) Can we control the letter images to be more defensive against adversarial attacks? For answering the first and second questions, we measure the defensibility of letters by employing Iterative Fast Gradient Sign Method (I-FGSM) and then build a deep regression model for estimating the defensibility of each letter image. We also propose a two-step method based on a generative adversarial network (GAN) for generating character images with higher defensibility, which solves the third research question.
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。
