Peiyuan Liu

Output-correlated adversarial attack for image translation network

2022 · Journal of Electronic Imaging

Maliciously forged images generated by image translation networks can cause significant security threats to personal privacy and national security. An emerging solution for forged images is preventing image forgery models from tampering with user images …

An adversarial attack method for Yolov4 based on changeable-perturbation-step PGD

2022

With the development of artificial intelligence, the object detection model based on deep learning has also achieved great results. The detection model has also developed from the traditional manual extraction of features to the current …