AED-PADA: Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation

H Peng, Y Wang, R Yang, B Li, R Wang… - ACM Transactions on …, 2025 - dl.acm.org
Adversarial example detection, which can be conveniently applied in many scenarios, is
important in the area of adversarial defense. Unfortunately, existing detection methods suffer …

Adversarial Robustness in RGB-Skeleton Action Recognition: Leveraging Attention Modality Reweighter

C Liu, X Liu, Z Yu, Y Hou, H Yue… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
Deep neural networks (DNNs) have been applied in many computer vision tasks and
achieved state-of-the-art (SOTA) performance. However, misclassification will occur when …

[PDF][PDF] Transparency and reliability assurance methods for safeguarding deep neural networks-a survey

E Haedecke, MA Pintz - … on Trustworthy Artificial Intelligence as a part of …, 2022 - hal.science
In light of deep neural network applications emerging in diverse fields–eg, industry,
healthcare or finance–weaknesses and failures of these models might bare unacceptable …

Learning Discriminative Features for Adversarial Robustness

R Hosler, T Phillips, X Yu, A Sundar… - … on Mobility, Sensing …, 2021 - ieeexplore.ieee.org
Deep Learning models have shown incredible image classification capabilities that extend
beyond humans. However, they remain susceptible to image perturbations that a human …