面向智能驾驶视觉感知的对抗样本攻击与防御方法综述

现如今，深度学习已然成为机器学习领域最热门的研究方向之一，其在图像识别、目标检测、语音处理、问答系统等诸多领域都取得了巨大成功.然而通过附加经过特殊设计的细微扰动而构造出的对抗样本，能够破坏深度模型的原有性能，其存在使许多对安全性能指标具有极高要求的技术领域，特别是以视觉感知为主要技术优先的智能驾驶系统，面临新的威胁和挑战.因此，对对抗样本的生成攻击和主动防御研究，成为深度学习和计算机视觉领域极为重要的交叉性研究课题.本文首先简述了对抗样本的相关概念，在此基础上详细介绍了一系列典型的对抗样本攻击和防御算法.随后，列举了针对视觉感知系统的多个物理世界攻击实例，探讨了其对智能驾驶领域的潜在影响.最后，对对抗样本的攻击与防御研究进行了技术展望.

A survey of adversarial attacks and defenses on visual perception in automatic driving

Nowadays,deep learning has become one of the hottest research directions in the field of machine learning.It has achieved great success in a wide range of fields such as image recognition,target detection,voice processing,and question answering system.However,the emergence of adversarial examples has triggered new thinking on deep learning.The performance of deep learning models can be destroyed by adversarial examples constructed by adding specially designed subtle disturbance.The existence of adversarial examples makes many technical fields with high requirements on safety performance face new threats and challenges,especially the automatic driving system which uses visual perception as the main technology priority.Therefore,the research on adversarial attack and active defense has become an extremely important cross-cutting research topic in the field of deep learning and computer vision.In this paper,relevant concepts on adversarial examples are summarized firstly,and then a series of typical adversarial attack methods and defense algorithms are introduced in detail.Subsequently,a number of physical world attacks against visual perception are introduced along with discussions on their potential impact on the field of automatic driving.Finally,we give a technical outlook on the future study of adversarial attacks and defenses.