Prompt engineering is a technique that involves augmenting a large pre-trained model with
task-specific hints, known as prompts, to adapt the model to new tasks. Prompts can be …

Backdoor defenses have been studied to alleviate the threat of deep neural networks
(DNNs) being backdoor attacked and thus maliciously altered. Since DNNs usually adopt …

Recent studies have demonstrated that existing deep neural networks (DNNs) on 3D point
clouds are vulnerable to adversarial examples, especially under the white-box settings …

Abstract Machine unlearning is an emerging task of removing the influence of selected
training datapoints from a trained model upon data deletion requests, which echoes the …

In this paper, we ask whether Vision Transformers (ViTs) can serve as an underlying
architecture for improving the adversarial robustness of machine learning models against …

Various adaptation methods, such as LoRA, prompts, and adapters, have been proposed to
enhance the performance of pre-trained vision-language models in specific domains. As test …

The emergence of Deep Neural Networks (DNNs) has revolutionized various domains,
enabling the resolution of complex tasks spanning image recognition, natural language …

Despite their success, vision transformers still remain vulnerable to image corruptions, such
as noise or blur. Indeed, we find that the vulnerability mainly stems from the unstable self …

Different from traditional task-specific vision models, recent large VLMs can readily adapt to
different vision tasks by simply using different textual instructions, ie, prompts. However, a …

Fast adversarial training (FAT) is an efficient method to improve robustness in white-box
attack scenarios. However, the original FAT suffers from catastrophic overfitting, which …