Search Results for author: Zhikai Chen

Found 4 papers, 0 papers with code

Enhancing the Transferability of Adversarial Attacks via Scale Ensemble

no code implementations29 Sep 2021 Xianfeng Gao, Zhikai Chen, Bo Zhang

The experiments on ImageNet show that our method successfully mitigates the gap of transferability between models with different input sizes and achieves about 8% higher success rate comparing with the state-of-the-art input transformation methods.

MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakes

no code implementations CVPR 2021 Zhikai Chen, Lingxi Xie, Shanmin Pang, Yong He, Bo Zhang

This paper presents MagDR, a mask-guided detection and reconstruction pipeline for defending deepfakes from adversarial attacks.

Appending Adversarial Frames for Universal Video Attack

no code implementations10 Dec 2019 Zhikai Chen, Lingxi Xie, Shanmin Pang, Yong He, Qi Tian

There have been many efforts in attacking image classification models with adversarial perturbations, but the same topic on video classification has not yet been thoroughly studied.

Classification Frame +3

Unsupervised Single Image Deraining with Self-supervised Constraints

no code implementations21 Nov 2018 Xin Jin, Zhibo Chen, Jianxin Lin, Zhikai Chen, Wei Zhou

Most existing single image deraining methods require learning supervised models from a large set of paired synthetic training data, which limits their generality, scalability and practicality in real-world multimedia applications.

Single Image Deraining

Cannot find the paper you are looking for? You can Submit a new open access paper.