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

Deep neural networks are susceptible to attacks from adversarial examples in recent years.
Especially the black-box attacks cause a more serious threat to practical applications …

Recent advances in deep learning have markedly improved autonomous driving (AD)
models, particularly end-to-end systems that integrate perception, prediction, and planning …

Due to the reliance on the cloud for training, multimodal learning models are vulnerable to
multimodal backdoor attacks. However, such attacks often use static trigger patterns, which …

Recently many approaches directly operate on point clouds for different tasks. These
approaches become more computation and storage demanding when point cloud size is …

Visual language pre-training (VLP) models have demonstrated significant success in
various domains, but they remain vulnerable to adversarial attacks. Addressing these …

The rapid progress in the reasoning capability of the Multi-modal Large Language Models
(MLLMs) has triggered the development of autonomous agent systems on mobile devices …

Autonomous driving technology has advanced significantly with deep learning, but noise
and attacks threaten its real-world deployment. While research has revealed vulnerabilities …

Despite the exceptional performance of multi-modal large language models (MLLMs), their
deployment requires substantial computational resources. Once malicious users induce …

Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by
enhancing reasoning capabilities. However, these models remain highly vulnerable to …