Diffusion models have emerged as a powerful new family of deep generative models with
record-breaking performance in many applications, including image synthesis, video …

Deep Learning is currently used to perform multiple tasks, such as object recognition, face
recognition, and natural language processing. However, Deep Neural Networks (DNNs) are …

Automated red teaming holds substantial promise for uncovering and mitigating the risks
associated with the malicious use of large language models (LLMs), yet the field lacks a …

The score-based generative model (SGM) has demonstrated remarkable performance in
addressing challenging under-determined inverse problems in medical imaging. However …

Are foundation models secure against malicious actors? In this work, we focus on the image
input to a vision-language model (VLM). We discover image hijacks, adversarial images that …

Abstract Large pre-trained Vision-Language Models (VLMs) like CLIP despite having
remarkable generalization ability are highly vulnerable to adversarial examples. This work …

In this paper, we delve deeper into the Kullback–Leibler (KL) Divergence loss and
mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) …

Diffusion models have been applied to improve adversarial robustness of image classifiers
by purifying the adversarial noises or generating realistic data for adversarial training …

Generative data augmentation, which scales datasets by obtaining fake labeled examples
from a trained conditional generative model, boosts classification performance in various …

In an effort to further advance semi-supervised generative and classification tasks, we
propose a simple yet effective training strategy called* dual pseudo training*(DPT), built …