Safety and Trustworthiness of Deep Neural Networks: A Survey
Safety and Trustworthiness of Deep Neural Networks: A Survey
复制标题
DOI：
--
复制
发表时间：
2018-12
期刊：
影响因子：
--
通讯作者：
Xiaowei Huang;D. Kroening;M. Kwiatkowska;Wenjie Ruan;Youcheng Sun;Emese Thamo;Min Wu;Xinping Yi-Xinpin
中科院分区：
文献类型：
--
作者：
Xiaowei Huang;D. Kroening;M. Kwiatkowska;Wenjie Ruan;Youcheng Sun;Emese Thamo;Min Wu;Xinping Yi-Xinpin
在过去的几年里，深度神经网络（DNN）在几项长期任务上实现人类智能方面取得了重大进展。随着DNN在各种应用中的广泛部署，人们对其安全性和可信度的担忧也在不断增加，特别是在自动驾驶汽车发生致命事故之后。解决这些问题的研究非常活跃，过去几年发表了许多论文。这份调查报告将对目前关于使DNN安全和可信的研究工作进行回顾，重点关注四个方面，即，验证、测试、对抗性攻击和防御以及可解释性。我们总共调查了178篇论文，其中大部分是最近两年发表的，即，2017年和2018年。
In the past few years, significant progress has been made on deep neural networks (DNNs) in achieving human-level intelligence on several long-standing tasks. With broader deployment of DNNs on various applications, the concerns on its safety and trustworthiness have been raised, particularly after the fatal incidents of self-driving cars. Research to address these concerns is very active, with many papers released in the past few years. This survey paper is to conduct a review of the current research efforts on making DNNs safe and trustworthy, by focusing on four aspects, i.e., verification, testing, adversarial attack and defence, and interpretability. In total, we surveyed 178 papers, most of which were published in the most recent two years, i.e., 2017 and 2018.