114 citations · 125 across the 13 of their papers we have counts for
7 papers · 1 filter
Robust Backdoor Attacks on Object Detection in Real World
Yaguan Qian, Boyuan Ji, Shuke He +4
Deep learning models are widely deployed in many applications, such as object detection in various security fields. However, these models are vulnerable to backdoor attacks. Most b…
Towards the Desirable Decision Boundary by Moderate-Margin Adversarial Training
Xiaoyu Liang, Yaguan Qian, Jianchang Huang +4
Adversarial training, as one of the most effective defense methods against adversarial attacks, tends to learn an inclusive decision boundary to increase the robustness of deep lea…
Edge-aware Guidance Fusion Network for RGB Thermal Scene Parsing
Wujie Zhou, Shaohua Dong, Caie Xu +1
RGB thermal scene parsing has recently attracted increasing research interest in the field of computer vision. However, most existing methods fail to perform good boundary extracti…
Versailles-FP dataset: Wall Detection in Ancient
Wassim Swaileh, Dimitrios Kotzinos, Suman Ghosh +3
Access to historical monuments' floor plans over a time period is necessary to understand the architectural evolution and history. Such knowledge bases also helps to rebuild the hi…
Person Re-identification based on Robust Features in Open-world
Yaguan Qian, Anlin Sun
Deep learning technology promotes the rapid development of person re-identifica-tion (re-ID). However, some challenges are still existing in the open-world. First, the existing re-…
Visually Imperceptible Adversarial Patch Attacks on Digital Images
Yaguan Qian, Jiamin Wang, Bin Wang +4
The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted more attention. Many algorithms have been proposed to craft powerful adversarial examples. Ho…
Spot Evasion Attacks: Adversarial Examples for License Plate Recognition Systems with Convolutional Neural Networks
Ya-guan Qian, Dan-feng Ma, Bin Wang +5
Recent studies have shown convolution neural networks (CNNs) for image recognition are vulnerable to evasion attacks with carefully manipulated adversarial examples. Previous work…