摘要
由一名新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-一项关于机器学习的新研究现在可以获得。根据来自澳大利亚布里斯班的新闻，NewsRx Co Rresponders，研究表明：“网络物理系统(CPS)越来越依赖于机器学习(ML)技术，以降低劳动力成本和提高效率。然而，ML的采用也使CPS面临文献中所见的潜在对抗性ML攻击。”我们的新闻记者从Queensland大学的研究中获得了一句话：“具体来说，CPS中互联网连接的增加导致了设备之间数据生成量和通信频率的激增，从而扩大了ML广告的攻击面和攻击机会。在各种对抗性ML攻击中，逃避攻击是最著名的攻击之一。因此，摘要:本文综述了近年来关于规避攻击和防御技术的最新研究成果,以了解当前计算机保护系统中最先进的ML模型安全性。为了评估攻击的有效性,本文提出了一种攻击分类方法,引入了扰动级别和修改特征数量等量化指标。同样,本文从四个方面介绍了一种防御分类法，从模型的输入到输出，展示了防御技术。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on Machine Learning is now available. According to news originating from Brisbane, Australia, by NewsRx co rrespondents, research stated, "Cyber-physical systems (CPS) are increasingly re lying on machine learning (ML) techniques to reduce labor costs and improve effi ciency. However, the adoption of ML also exposes CPS to potential adversarial ML attacks witnessed in the literature." Our news journalists obtained a quote from the research from the University of Q ueensland, "Specifically, the increased Internet connectivity in CPS has resulte d in a surge in the volume of data generation and communication frequency among devices, thereby expanding the attack surface and attack opportunities for ML ad versaries. Among various adversarial ML attacks, evasion attacks are one of the most well-known ones. Therefore, this survey focuses on summarizing the latest r esearch on evasion attack and defense techniques, to understand state-of-the-art ML model security in CPS. To assess the attack effectiveness, this survey propo ses an attack taxonomy by introducing quantitative measures such as per-turbation level and the number of modified features. Similarly, a defense taxonomy is int roduced based on four perspectives demonstrating the defensive techniques from m odels' inputs to their outputs."
NETL
NSTL