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 …

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 …

Adversarial phenomenon has been widely observed in machine learning (ML) systems,
especially in those using deep neural networks, describing that ML systems may produce …

Watermarking has been widely adopted for protecting the intellectual property (IP) of Deep
Neural Networks (DNN) to defend the unauthorized distribution. Unfortunately, studies have …

Skip connections are fundamental architecture designs for modern deep neural networks
(DNNs) such as CNNs and ViTs. While they help improve model performance significantly …

Federated self-supervised learning (FSSL) has recently emerged as a promising paradigm
that enables the exploitation of clients' vast amounts of unlabeled data while preserving data …

Backdoor attacks present a substantial security concern for deep learning models,
especially those utilized in applications critical to safety and security. These attacks …

Currently, sample-specific backdoor attacks (SSBAs) are the most advanced and malicious
methods since they can easily circumvent most of the current backdoor defenses. In this …

Deep neural networks (DNNs) are susceptible to backdoor attacks due to their black-box
nature and lack of interpretability. Backdoor attacks intend to manipulate the model's …

Deep Neural Networks (DNNs) have been widely used in many areas such as autonomous
driving and face recognition. However, DNN model is fragile to backdoor attack. A backdoor …