Z Song, X Yang, Z Xu, I King - IEEE Transactions on Neural …, 2022 - ieeexplore.ieee.org
Semi-supervised learning (SSL) has tremendous value in practice due to the utilization of both labeled and unlabelled data. An essential class of SSL methods, referred to as graph …
The field of graph neural networks (GNNs) has seen rapid and incredible strides over the recent years. Graph neural networks, also known as deep learning on graphs, graph …
Graph Neural Networks (GNNs) are powerful tools in representation learning for graphs. However, recent studies show that GNNs are vulnerable to carefully-crafted perturbations …
X Zhang, M Zitnik - Advances in neural information …, 2020 - proceedings.neurips.cc
Deep learning methods for graphs achieve remarkable performance on many tasks. However, despite the proliferation of such methods and their success, recent findings …
N Carlini, A Terzis - arXiv preprint arXiv:2106.09667, 2021 - arxiv.org
Multimodal contrastive learning methods like CLIP train on noisy and uncurated training datasets. This is cheaper than labeling datasets manually, and even improves out-of …
Adversarial Attacks and Defenses on Graphs Page 1 Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies Wei Jin†, Yaxin Li†, Han Xu†, Yiqi Wang† …
Y Li, T Zhai, B Wu, Y Jiang, Z Li, S Xia - arXiv preprint arXiv:2004.04692, 2020 - arxiv.org
Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of the infected model will be maliciously changed if the hidden …
Z Xi, R Pang, S Ji, T Wang - 30th USENIX Security Symposium (USENIX …, 2021 - usenix.org
One intriguing property of deep neural networks (DNNs) is their inherent vulnerability to backdoor attacks—a trojan model responds to trigger-embedded inputs in a highly …
Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can …