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 …

Diffusion models are generative models, which gradually add and remove noise to learn the
underlying distribution of training data for data generation. The components of diffusion …

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

Latent diffusion models achieve state-of-the-art performance on a variety of generative tasks,
such as image synthesis and image editing. However, the robustness of latent diffusion …

While generative diffusion models excel in producing high-quality images, they can also be
misused to mimic authorized images, posing a significant threat to AI systems. Efforts have …

Most adversarial attacks and defenses focus on perturbations within small $\ell_p $-norm
constraints. However, $\ell_p $ threat models cannot capture all relevant semantic …

Denoising probabilistic diffusion models have shown breakthrough performance to generate
more photo-realistic images or human-level illustrations than the prior models such as …

We propose Instruct2Attack (I2A), a language-guided semantic attack that generates
semantically meaningful perturbations according to free-form language instructions. We …

Adversarial patch attacks which can mislead deep learning models and the human eye in
both the digital and physical domains have led to a trust crisis. Traditional approaches to …

Recent image harmonization methods have demonstrated promising results. However, due
to their heavy reliance on a large number of composite images, these works are expensive …