With the significant development of large models in recent years, Large Vision-Language
Models (LVLMs) have demonstrated remarkable capabilities across a wide range of …

Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities that
increasingly influence various aspects of our daily lives, constantly defining the new …

As a prominent subfield of Artificial Intelligence Generated Content (AIGC), video generation
has achieved notable advancements in recent years. The introduction of Sora-alike models …

The vulnerability of deep neural networks to imperceptible adversarial perturbations has
attracted widespread attention. Inspired by the success of vision-language foundation …

Adversarial attacks, which manipulate input data to undermine model availability and
integrity, pose significant security threats during machine learning inference. With the advent …

With the continuous development of large language models (LLMs), transformer-based
models have made groundbreaking advances in numerous natural language processing …

Large Vision-Language Models (LVLMs) have shown significant progress in responding
well to visual-instructions from users. However, these instructions, encompassing images …

Large pre-trained Vision-Language Models (VLMs) such as Contrastive Language-Image
Pre-Training (CLIP) have been shown to be susceptible to adversarial attacks, raising …

Multimodal contrastive learning models (eg, CLIP) can learn high-quality representations
from large-scale image-text datasets, yet they exhibit significant vulnerabilities to backdoor …

Large visual language models like Contrastive Language-Image Pre-training (CLIP), despite
their excellent performance, are highly vulnerable to the influence of adversarial examples …