Can We Rely on AI?
Can We Rely on AI?
复制标题
DOI：
10.48550/arxiv.2308.15092
复制
发表时间：
2023-08
期刊：
影响因子：
--
通讯作者：
D. Higham
中科院分区：
文献类型：
--
作者：
D. Higham
在过去的十年里，对抗性攻击算法揭示了深度学习工具的不稳定性。这些算法提出了人工智能中的安全性、可靠性和可解释性问题；特别是在高风险环境中。从实践的角度来看，那些制定攻防战略的人之间已经发生了一场不断升级的战争。在更理论的层面上，研究人员还研究了有关攻击的存在和可计算性的更大问题。在这里，我们对这个主题做一个简要的概述，集中在应用数学和计算数学研究人员可能感兴趣的方面。
Over the last decade, adversarial attack algorithms have revealed instabilities in deep learning tools. These algorithms raise issues regarding safety, reliability and interpretability in artificial intelligence; especially in high risk settings. From a practical perspective, there has been a war of escalation between those developing attack and defence strategies. At a more theoretical level, researchers have also studied bigger picture questions concerning the existence and computability of attacks. Here we give a brief overview of the topic, focusing on aspects that are likely to be of interest to researchers in applied and computational mathematics.