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 …

Given the power of vision transformers a new learning paradigm pre-training and then
prompting makes it more efficient and effective to address downstream visual recognition …

Abstract Vision Transformers (ViTs) have demonstrated the state-of-the-art performance in
various vision-related tasks. The success of ViTs motivates adversaries to perform backdoor …

Recently, the backdoor attack on deep neural networks (DNNs) has been extensively
studied, which causes the backdoored models to behave well on benign samples, whereas …

Abstract Vision Transformers (ViTs) have a radically different architecture with significantly
less inductive bias than Convolutional Neural Networks. Along with the improvement in …

The backdoor attack on deep neural network models implants malicious data patterns in a
model to induce attacker-desirable behaviors. Existing defense methods fall into the online …

Transformer architectures are based on self-attention mechanism that processes images as
a sequence of patches. As their design is quite different compared to CNNs, it is important to …

Deep neural networks (DNNs) typically require massive data to train on, which is a hurdle for
numerous practical domains. Facing the data shortfall, one viable option is to acquire …

Given the pervasive use of deep learning models across various domains, ensuring model
security has emerged as a critical concern. This paper examines backdoor attacks, a form of …

Vision Transformers (ViT) have recently demonstrated exemplary performance on a variety
of vision tasks and are being used as an alternative to CNNs. Their design is based on a self …