4 papers
Towards Interpretable Adversarial Examples via Sparse Adversarial Attack
Fudong Lin, Jiadong Lou, Hao Wang +2
Sparse attacks are to optimize the magnitude of adversarial perturbations for fooling deep neural networks (DNNs) involving only a few perturbed pixels (i.e., under the l0 constrai…
GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models
Jiadong Lou, Xu Yuan, Rui Zhang +3
Graph neural networks (GNNs) have exhibited superior performance in various classification tasks on graph-structured data. However, they encounter the potential vulnerability from…
Variational Autoencoder Framework for Hyperspectral Retrievals (Hyper-VAE) of Phytoplankton Absorption and Chlorophyll a in Coastal Waters for NASA's EMIT and PACE Missions
Jiadong Lou, Bingqing Liu, Yuanheng Xiong +2
Phytoplankton absorb and scatter light in unique ways, subtly altering the color of water, changes that are often minor for human eyes to detect but can be captured by sensitive oc…
Towards Robust Vision Transformer via Masked Adaptive Ensemble
Fudong Lin, Jiadong Lou, Xu Yuan +1
Adversarial training (AT) can help improve the robustness of Vision Transformers (ViT) against adversarial attacks by intentionally injecting adversarial examples into the training…