activity
20172025
most citedSkip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets

177 citations · 611 across the 24 of their papers we have counts for

collaborators
Showing 2020Show all

7 papers · 1 filter

cs.CV20202 cited

Short-Term and Long-Term Context Aggregation Network for Video Inpainting

Ang Li, Shanshan Zhao, Xingjun Ma +5

Video inpainting aims to restore missing regions of a video and has many applications such as video editing and object removal. However, existing methods either suffer from inaccur…

cs.CR202031 cited

How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning

Lingjuan Lyu, Yitong Li, Karthik Nandakumar +2

This paper firstly considers the research problem of fairness in collaborative deep learning, while ensuring privacy. A novel reputation system is proposed through digital tokens a…

cs.CV202038 cited

Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks

Yunfei Liu, Xingjun Ma, James Bailey +1

Recent studies have shown that DNNs can be compromised by backdoor attacks crafted at training time. A backdoor attack installs a backdoor into the victim model by injecting a back…

cs.LG2020125 cited

Normalized Loss Functions for Deep Learning with Noisy Labels

Xingjun Ma, Hanxun Huang, Yisen Wang +3

Robust loss functions are essential for training accurate deep neural networks (DNNs) in the presence of noisy (incorrect) labels. It has been shown that the commonly used Cross En…

cs.CV2020

Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles

Ranjie Duan, Xingjun Ma, Yisen Wang +3

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. Existing works have mostly focused on either digital adversarial examples created via small and impe…

cs.CV2020

Clean-Label Backdoor Attacks on Video Recognition Models

Shihao Zhao, Xingjun Ma, Xiang Zheng +3

Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean tes…