activity
20202025
most citedCompression-Resistant Backdoor Attack against Deep Neural Networks

16 citations · 24 across the 3 of their papers we have counts for

collaborators

10 papers

cs.CR2025

Adversarial Example Based Fingerprinting for Robust Copyright Protection in Split Learning

Zhangting Lin, Mingfu Xue, Kewei Chen +5

Currently, deep learning models are easily exposed to data leakage risks. As a distributed model, Split Learning thus emerged as a solution to address this issue. The model is spli…

cs.CV2022★ 8 cited

Imperceptible and Multi-channel Backdoor Attack against Deep Neural Networks

Mingfu Xue, Shifeng Ni, Yinghao Wu +3

Recent researches demonstrate that Deep Neural Networks (DNN) models are vulnerable to backdoor attacks. The backdoored DNN model will behave maliciously when images containing bac…

cs.CV2022★ 16 cited

Compression-Resistant Backdoor Attack against Deep Neural Networks

Mingfu Xue, Xin Wang, Shichang Sun +3

In recent years, many backdoor attacks based on training data poisoning have been proposed. However, in practice, those backdoor attacks are vulnerable to image compressions. When…

cs.CV2021

Detecting Backdoor in Deep Neural Networks via Intentional Adversarial Perturbations

Mingfu Xue, Yinghao Wu, Zhiyu Wu +3

Recent researches show that deep learning model is susceptible to backdoor attacks. Many defenses against backdoor attacks have been proposed. However, existing defense works requi…

cs.MM2021

Detect and remove watermark in deep neural networks via generative adversarial networks

Haoqi Wang, Mingfu Xue, Shichang Sun +3

Deep neural networks (DNN) have achieved remarkable performance in various fields. However, training a DNN model from scratch requires a lot of computing resources and training dat…

cs.CR2021

AdvParams: An Active DNN Intellectual Property Protection Technique via Adversarial Perturbation Based Parameter Encryption

Mingfu Xue, Zhiyu Wu, Jian Wang +2

A well-trained DNN model can be regarded as an intellectual property (IP) of the model owner. To date, many DNN IP protection methods have been proposed, but most of them are water…