Zobrazeno 1 - 10
of 166
pro vyhledávání: '"Guo, Yuanfang"'
Deep neural networks are vulnerable to backdoor attacks. Among the existing backdoor defense methods, trigger reverse engineering based approaches, which reconstruct the backdoor triggers via optimizations, are the most versatile and effective ones c
Externí odkaz:
http://arxiv.org/abs/2404.12852
Adversarial example detection, which can be conveniently applied in many scenarios, is important in the area of adversarial defense. Unfortunately, existing detection methods suffer from poor generalization performance, because their training process
Externí odkaz:
http://arxiv.org/abs/2404.12635
Graphs with heterophily have been regarded as challenging scenarios for Graph Neural Networks (GNNs), where nodes are connected with dissimilar neighbors through various patterns. In this paper, we present theoretical understandings of the impacts of
Externí odkaz:
http://arxiv.org/abs/2401.09125
With the rapid development of the image generation technologies, the malicious abuses of the GAN-generated fingerprint images poses a significant threat to the public safety in certain circumstances. Although the existing universal deep forgery detec
Externí odkaz:
http://arxiv.org/abs/2308.09285
This paper focuses on an important type of black-box attacks, i.e., transfer-based adversarial attacks, where the adversary generates adversarial examples by a substitute (source) model and utilize them to attack an unseen target model, without knowi
Externí odkaz:
http://arxiv.org/abs/2307.00274
Graph Neural Networks (GNNs) have shown remarkable success in graph representation learning. Unfortunately, current weight assignment schemes in standard GNNs, such as the calculation based on node degrees or pair-wise representations, can hardly be
Externí odkaz:
http://arxiv.org/abs/2302.03228
The current success of Graph Neural Networks (GNNs) usually relies on loading the entire attributed graph for processing, which may not be satisfied with limited memory resources, especially when the attributed graph is large. This paper pioneers to
Externí odkaz:
http://arxiv.org/abs/2210.13149
Publikováno v:
IEEE Transactions on Big Data 9 (2023) 1697-1710
Graph Neural Networks (GNNs) have been generalized to process the heterogeneous graphs by various approaches. Unfortunately, these approaches usually model the heterogeneity via various complicated modules. This paper aims to propose a simple yet eff
Externí odkaz:
http://arxiv.org/abs/2209.11414
Publikováno v:
In Learning and Individual Differences July 2024 113
The transferability and robustness of adversarial examples are two practical yet important properties for black-box adversarial attacks. In this paper, we explore effective mechanisms to boost both of them from the perspective of network hierarchy, w
Externí odkaz:
http://arxiv.org/abs/2108.07033