Related Experiment Videos

Blind object detectors via transferable background adversarial attack

Jiawei Lian1, Shaohui Mei2, Xiaofei Wang2

  • 1School of Electronics and Information, Northwestern Polytechnical University, Xi'an, 710129, China; Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR, China.

Summary

This study introduces a novel background adversarial attack framework for deep neural networks (DNNs). The research highlights the critical role of background variations in DNN vulnerabilities, impacting machine vision robustness.

Related Concept Videos