Data poisoning attacks manipulate training data to introduce unexpected behaviors into
machine learning models at training time. For text-to-image generative models with massive …

Fine-tuning pre-trained models for downstream tasks has led to a proliferation of open-
sourced task-specific models. Recently, Model Merging (MM) has emerged as an effective …

Self-supervised learning (SSL) is a prevalent approach for encoding data representations.
Using a pre-trained SSL image encoder and subsequently training a downstream classifier …

Trained on billions of images, diffusion-based text-to-image models seem impervious to
traditional data poisoning attacks, which typically require poison samples approaching 20 …

In recent years there has been enormous interest in vision-language models trained using
self-supervised objectives. However the use of large-scale datasets scraped from the web …

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 …

Few-shot classification with foundation models (eg, CLIP, DINOv2, PaLM-2) enables users
to build an accurate classifier with a few labeled training samples (called support samples) …

Recent advancements in deep learning have substantially boosted the performance of
monocular depth estimation (MDE), an essential component in fully-vision-based …

Contrastive Learning (CL) has attracted enormous attention due to its remarkable capability
in unsupervised representation learning. However, recent works have revealed the …

Deep Learning's integration into critical sectors like autonomous vehicles and healthcare
diagnosis underscores the necessity for creating learning methods that are safe, secure …