Self-supervised learning is widely used in various domains for building foundation models. It
has been demonstrated to achieve state-of-the-art performance in a range of tasks. In the …

Text-to-Image generation models have revolutionized the artwork design process and
enabled anyone to create high-quality images by entering text descriptions called prompts …

Backdoor attacks represent one of the major threats to machine learning models. Various
efforts have been made to mitigate backdoors. However, existing defenses have become …

Pre-trained models (PTMs) are extensively utilized in various downstream tasks. Adopting
untrusted PTMs may suffer from backdoor attacks, where the adversary can compromise the …

In recent years, foundation models (FMs) have contributed heavily to the advancements in
the deep learning domain. By extracting intricate patterns from vast datasets, these models …

Large-scale unlabeled data has spurred recent progress in self-supervised learning
methods for learning rich visual representations. Masked autoencoders (MAE), a recently …

Pre-trained models (PTMs) are widely adopted across various downstream tasks in the
machine learning supply chain. Adopting untrustworthy PTMs introduces significant security …

Text-to-Image generation models have revolutionized the artwork design process and
enabled anyone to create high-quality images by entering text descriptions called prompts …

In recent years, foundation models (FMs) have solidified their role as cornerstone
advancements in the deep learning domain. By extracting intricate patterns from vast …