Search Results for author: Yufan Wu

Found 4 papers, 2 papers with code

Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense

no code implementations14 Apr 2023 Jingyuan Wang, Yufan Wu, Mingxuan Li, Xin Lin, Junjie Wu, Chao Li

While having achieved great success in rich real-life applications, deep neural network (DNN) models have long been criticized for their vulnerability to adversarial attacks.

ConvTransformer: A Convolutional Transformer Network for Video Frame Synthesis

2 code implementations20 Nov 2020 Zhouyong Liu, Shun Luo, Wubin Li, Jingben Lu, Yufan Wu, Shilei Sun, ChunGuo Li, Luxi Yang

To the best of our knowledge, this is the first time that ConvTransformer architecture is proposed and applied to video frame synthesis.

Are L2 adversarial examples intrinsically different?

no code implementations28 Feb 2020 Mingxuan Li, Jingyuan Wang, Yufan Wu

That is, adversarial examples generated by $L_2$ attacks usually have larger input sensitivity which can be used to identify them efficiently.

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