Improving the transferability of adversarial samples by path-augmented method
Deep neural networks have achieved unprecedented success on diverse vision tasks.
However, they are vulnerable to adversarial noise that is imperceptible to humans. This …
However, they are vulnerable to adversarial noise that is imperceptible to humans. This …
Transferable adversarial attacks on vision transformers with token gradient regularization
Vision transformers (ViTs) have been successfully deployed in a variety of computer vision
tasks, but they are still vulnerable to adversarial samples. Transfer-based attacks use a local …
tasks, but they are still vulnerable to adversarial samples. Transfer-based attacks use a local …
Diffute: Universal text editing diffusion model
Diffusion model based language-guided image editing has achieved great success recently.
However, existing state-of-the-art diffusion models struggle with rendering correct text and …
However, existing state-of-the-art diffusion models struggle with rendering correct text and …
Hierarchical dynamic image harmonization
Image harmonization is a critical task in computer vision, which aims to adjust the
foreground to make it compatible with the background. Recent works mainly focus on using …
foreground to make it compatible with the background. Recent works mainly focus on using …
Adversarial Training: A Survey
Adversarial training (AT) refers to integrating adversarial examples--inputs altered with
imperceptible perturbations that can significantly impact model predictions--into the training …
imperceptible perturbations that can significantly impact model predictions--into the training …
Backpropagation path search on adversarial transferability
Deep neural networks are vulnerable to adversarial examples, dictating the imperativeness
to test the model's robustness before deployment. Transfer-based attackers craft adversarial …
to test the model's robustness before deployment. Transfer-based attackers craft adversarial …
Towards transferable adversarial attacks on vision transformers for image classification
The deployment of high-performance Vision Transformer (ViT) models has garnered
attention from both industry and academia. However, their vulnerability to adversarial …
attention from both industry and academia. However, their vulnerability to adversarial …
Edge Detectors Can Make Deep Convolutional Neural Networks More Robust
J Ding, JC Zhao, YZ Sun, P Tan, JW Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Deep convolutional neural networks (DCNN for short) are vulnerable to examples with small
perturbations. Improving DCNN's robustness is of great significance to the safety-critical …
perturbations. Improving DCNN's robustness is of great significance to the safety-critical …
Improving the Robustness of Deep Convolutional Neural Networks Through Feature Learning
J Ding, JC Zhao, YZ Sun, P Tan, JE Ma… - arXiv preprint arXiv …, 2023 - arxiv.org
Deep convolutional neural network (DCNN for short) models are vulnerable to examples
with small perturbations. Adversarial training (AT for short) is a widely used approach to …
with small perturbations. Adversarial training (AT for short) is a widely used approach to …
A Patch-wise Adversarial Denoising Could Enhance the Robustness of Adversarial Training
S Zhao, S Liu, B Zhang, Y Zhai, Z Liu… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
The adversarial examples have demonstrated the vulnerability of machine learning models.
While the data augmentation strategy has been a cornerstone in circumventing overfitting …
While the data augmentation strategy has been a cornerstone in circumventing overfitting …