Cca: Exploring The Possibility Of Contextual Camouflage Attack On Object Detection
2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)(2020)
摘要
Deep neural network based object detection has become the cornerstone of many real-world applications. Along with this success comes concerns about its vulnerability to malicious attacks. To gain more insight into this issue, we propose a contextual camouflage attack (CCA for short) algorithm to influence the performance of object detectors. In this paper, we use an evolutionary search strategy and adversarial machine learning in interactions with a photo-realistic simulated environment to find camouflage patterns that are effective over a huge variety of object locations, camera poses, and lighting conditions. The proposed camouflages are validated effective to most of the state-of-the-art object detectors.
更多查看译文
关键词
CCA,contextual camouflage attack,object detection,deep neural network,real-world applications,malicious attacks,evolutionary search strategy,adversarial machine learning,camouflage patterns,object locations,state-of-the-art object detectors,photorealistic simulated environment,camera poses,lighting conditions
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要