Multimodal fake news detection through data augmentation-based contrastive learning
During the information exploding era, news can be created or edited purposely for
promoting the spreading of social influence. However, unverified or fabricated news can …
promoting the spreading of social influence. However, unverified or fabricated news can …
Rethinking weakly-supervised video temporal grounding from a game perspective
This paper addresses the challenging task of weakly-supervised video temporal grounding.
Existing approaches are generally based on the moment proposal selection framework that …
Existing approaches are generally based on the moment proposal selection framework that …
Deep manifold attack on point clouds via parameter plane stretching
Adversarial attack on point clouds plays a vital role in evaluating and improving the
adversarial robustness of 3D deep learning models. Current attack methods are mainly …
adversarial robustness of 3D deep learning models. Current attack methods are mainly …
Unsupervised feature selection through combining graph learning and ℓ2, 0-norm constraint
Graph-based unsupervised feature selection algorithms have been shown to be promising
for handling unlabeled and high-dimensional data. Whereas, the vast majority of those …
for handling unlabeled and high-dimensional data. Whereas, the vast majority of those …
Uncertainty-aware distillation for semi-supervised few-shot class-incremental learning
Given a model well-trained with a large-scale base dataset, few-shot class-incremental
learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples …
learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples …
Rethinking perturbation directions for imperceptible adversarial attacks on point clouds
Adversarial attacks have been successfully extended to the field of point clouds. Besides
applying the common perturbation guided by the gradient, adversarial attacks on point …
applying the common perturbation guided by the gradient, adversarial attacks on point …
The cascaded forward algorithm for neural network training
Backpropagation (BP) algorithm has played a significant role in the development of deep
learning. However, there exist some limitations associated with this algorithm, such as …
learning. However, there exist some limitations associated with this algorithm, such as …
ADS-detector: An attention-based dual stream adversarial example detection method
S Guo, X Li, P Zhu, Z Mu - Knowledge-Based Systems, 2023 - Elsevier
Adversarial attacks seriously threaten the security of machine learning models. Thus,
detecting adversarial examples has become an important and interesting research topic …
detecting adversarial examples has become an important and interesting research topic …
Flat: flux-aware imperceptible adversarial attacks on 3D point clouds
Adversarial attacks on point clouds play a vital role in assessing and enhancing the
adversarial robustness of 3D deep learning models. While employing a variety of geometric …
adversarial robustness of 3D deep learning models. While employing a variety of geometric …
SGMA: a novel adversarial attack approach with improved transferability
Deep learning models are easily deceived by adversarial examples, and transferable
attacks are crucial because of the inaccessibility of model information. Existing SOTA attack …
attacks are crucial because of the inaccessibility of model information. Existing SOTA attack …