How deep learning sees the world: A survey on adversarial attacks & defenses
Deep Learning is currently used to perform multiple tasks, such as object recognition, face
recognition, and natural language processing. However, Deep Neural Networks (DNNs) are …
recognition, and natural language processing. However, Deep Neural Networks (DNNs) are …
Transferable adversarial attack for both vision transformers and convolutional networks via momentum integrated gradients
W Ma, Y Li, X Jia, W Xu - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Abstract Visual Transformers (ViTs) and Convolutional Neural Networks (CNNs) are the two
primary backbone structures extensively used in various vision tasks. Generating …
primary backbone structures extensively used in various vision tasks. Generating …
Towards efficient adversarial training on vision transformers
Abstract Vision Transformer (ViT), as a powerful alternative to Convolutional Neural Network
(CNN), has received much attention. Recent work showed that ViTs are also vulnerable to …
(CNN), has received much attention. Recent work showed that ViTs are also vulnerable to …
Revisiting adversarial training for imagenet: Architectures, training and generalization across threat models
While adversarial training has been extensively studied for ResNet architectures and low
resolution datasets like CIFAR-10, much less is known for ImageNet. Given the recent …
resolution datasets like CIFAR-10, much less is known for ImageNet. Given the recent …
Robustifying token attention for vision transformers
Despite the success of vision transformers (ViTs), they still suffer from significant drops in
accuracy in the presence of common corruptions, such as noise or blur. Interestingly, we …
accuracy in the presence of common corruptions, such as noise or blur. Interestingly, we …
Are vision transformers robust to patch perturbations?
Abstract Recent advances in Vision Transformer (ViT) have demonstrated its impressive
performance in image classification, which makes it a promising alternative to Convolutional …
performance in image classification, which makes it a promising alternative to Convolutional …
You Are Catching My Attention: Are Vision Transformers Bad Learners under Backdoor Attacks?
Abstract Vision Transformers (ViTs), which made a splash in the field of computer vision
(CV), have shaken the dominance of convolutional neural networks (CNNs). However, in the …
(CV), have shaken the dominance of convolutional neural networks (CNNs). However, in the …
Give me your attention: Dot-product attention considered harmful for adversarial patch robustness
Neural architectures based on attention such as vision transformers are revolutionizing
image recognition. Their main benefit is that attention allows reasoning about all parts of a …
image recognition. Their main benefit is that attention allows reasoning about all parts of a …
Jailbreaking attack against multimodal large language model
This paper focuses on jailbreaking attacks against multi-modal large language models
(MLLMs), seeking to elicit MLLMs to generate objectionable responses to harmful user …
(MLLMs), seeking to elicit MLLMs to generate objectionable responses to harmful user …
Self-ensembling vision transformer (sevit) for robust medical image classification
Abstract Vision Transformers (ViT) are competing to replace Convolutional Neural Networks
(CNN) for various computer vision tasks in medical imaging such as classification and …
(CNN) for various computer vision tasks in medical imaging such as classification and …