.png){kind=icon}
返回
Adversarial Examples on Object Recognition: A Comprehensive Survey
.png){kind=icon}
OA
AI
DOI：10.1145/3398394.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect behavior. Such perturbations, called adversarial examples, are intentionally designed to test the network's sensitivity to distribution drifts. Given their surprisingly small size, a wide body of literature conjectures on their existence and how this phenomenon can be mitigated. In this article, we discuss the impact of adversarial examples on security, safety, and robustness of neural networks. We start by introducing the hypotheses behind their existence, the methods used to construct or protect against them, and the capacity to transfer adversarial examples between different machine learning models. Altogether, the goal is to provide a comprehensive and self-contained survey of this growing field of research.
Keyword:
Adversarial examples
machine learning
security
robustness
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
28
论文数:
2.4K
被引数:
3.5W
机构
引用论文
Welding characteristics of aluminum, copper, nickel and aluminum alloy with alumina coating using ultrasonic complex vibration welding equipments铝、铜、镍及铝合金氧化铝涂层超声复合振动焊接特性研究
PREAI
分享收藏Copper-doped silica cuprous sulfate (CDSCS) as a highly efficient and new heterogeneous nano catalyst for [3+2] Huisgen cycloaddition.png)
Tetrahedron
TetrahedronIF0
PREAI
分享收藏分享收藏
查看更多内容