论文标题
雅典娜：基于各种弱防御措施的框架来建立对抗性防御
ATHENA: A Framework based on Diverse Weak Defenses for Building Adversarial Defense
论文作者
论文摘要
关于针对对抗性攻击的防御技术已经进行了广泛的研究。但是，它们主要是为特定模型家族或应用程序域而设计的，因此，它们不能轻易扩展。根据各种弱防御能力的合奏的设计理念，我们提出了雅典娜 - 这是一个灵活而可扩展的框架，用于建立一般但有效的防御能力，以防止对抗性攻击。我们已经进行了一项全面的实证研究，以评估雅典娜的几种实现，其中包括零知识，黑盒，灰色盒子和白盒在内的四个威胁模型。我们还解释了（i）为什么多样性重要，（ii）防御框架的一般性以及（iii）雅典娜产生的间接费用。
There has been extensive research on developing defense techniques against adversarial attacks; however, they have been mainly designed for specific model families or application domains, therefore, they cannot be easily extended. Based on the design philosophy of ensemble of diverse weak defenses, we propose ATHENA---a flexible and extensible framework for building generic yet effective defenses against adversarial attacks. We have conducted a comprehensive empirical study to evaluate several realizations of ATHENA with four threat models including zero-knowledge, black-box, gray-box, and white-box. We also explain (i) why diversity matters, (ii) the generality of the defense framework, and (iii) the overhead costs incurred by ATHENA.
