首页|Research Reports from Wuhan Institute of Technology Provide New Insights into Robotics (Attacking Robot Vision Models Efficiently Based on Improved Fast Gradient Sign Method)
Research Reports from Wuhan Institute of Technology Provide New Insights into Robotics (Attacking Robot Vision Models Efficiently Based on Improved Fast Gradient Sign Method)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Mdpi
Investigators publish new report on robotics. According to news reporting from Wuhan, People's Republic of China, by NewsRx journalists, research stated, "The robot vision model is the basis for the robot to perceive and understand the environment and make correct decisions." Financial supporters for this research include National Natural Science Foundation of China. The news journalists obtained a quote from the research from Wuhan Institute of Technology: "However, the security and stability of robot vision models are seriously threatened by adversarial examples. In this study, we propose an adversarial attack algorithm, RMS-FGSM, for robot vision models based on root-mean-square propagation (RMSProp). RMS-FGSM uses an exponentially weighted moving average (EWMA) to reduce the weight of the historical cumulative squared gradient. Additionally, it can suppress the gradient growth based on an adaptive learning rate. By integrating with the RMSProp, RMS-FGSM is more likely to generate optimal adversarial examples, and a high attack success rate can be achieved."
Wuhan Institute of TechnologyWuhanPeople's Republic of ChinaAsiaEmerging TechnologiesMachine LearningRobotRobotics
NETL
NSTL
Mdpi
