相关论文: Towards Transferable Attacks Against Vision-LLMs i…

A reliable driving assistant should provide consistent responses based on temporally grounded reasoning derived from observed information. In this work, we investigate whether Vision-Language Models (VLMs), when applied as driving…

Vision-Language Navigation (VLN) presents a unique challenge for Large Vision-Language Models (VLMs) due to their inherent architectural mismatch: VLMs are primarily pretrained on static, disembodied vision-language tasks, which…

The rapid development of Large Language Models (LLMs) has brought impressive advancements across various tasks. However, despite these achievements, LLMs still pose inherent safety risks, especially in the context of jailbreak attacks. Most…

The integration of visual and textual data in Vision-Language Pre-training (VLP) models is crucial for enhancing vision-language understanding. However, the adversarial robustness of these models, especially in the alignment of image-text…

Vision-language models are emerging for autonomous driving, yet their robustness to physical adversarial attacks remains unexplored. This paper presents a systematic framework for comparative adversarial evaluation across three VLM…

Vision-Language-Action models (VLAs) have recently demonstrated remarkable progress in embodied environments, enabling robots to perceive, reason, and act through unified multimodal understanding. Despite their impressive capabilities, the…

Today's advanced driver assistance systems (ADAS), like adaptive cruise control or rear collision warning, are finding broader adoption across vehicle classes. Integrating such advanced, multimodal Large Language Models (LLMs) on board a…

As Vision-Language Models (VLMs) demonstrate increasing capabilities across real-world applications such as code generation and chatbot assistance, ensuring their safety has become paramount. Unlike traditional Large Language Models (LLMs),…

Ensuring and improving the safety of autonomous driving systems (ADS) is crucial for the deployment of highly automated vehicles, especially in safety-critical events. To address the rarity issue, adversarial scenario generation methods are…

Large Language Models (LLMs) have demonstrated impressive capabilities, yet their deployment in high-stakes domains is hindered by inherent limitations in trustworthiness, including hallucinations, instability, and a lack of transparency.…

Vision Language Models (VLMs) have advanced perception in autonomous driving (AD), but they remain vulnerable to adversarial threats. These risks range from localized physical patches to imperceptible global perturbations. Existing defense…

The safe deployment of autonomous driving (AD) systems is fundamentally hindered by the long-tail problem, where rare yet critical driving scenarios are severely underrepresented in real-world data. Existing solutions including…

Adversarial attacks aim to generate malicious inputs that mislead deep models, but beyond causing model failure, they cannot provide certain interpretable information such as ``\textit{What content in inputs make models more likely to…

Generative large vision-language models (LVLMs) have recently achieved impressive performance gains, and their user base is growing rapidly. However, the security of LVLMs, in particular in a long-context multi-turn setting, is largely…

End-to-end autonomous driving frameworks face persistent challenges in generalization, training efficiency, and interpretability. While recent methods leverage Vision-Language Models (VLMs) through supervised learning on large-scale…

The rapid progress of auto-regressive vision-language models (VLMs) has inspired growing interest in vision-language-action models (VLA) for robotic manipulation. Recently, masked diffusion models, a paradigm distinct from autoregressive…

Vision-Language Models (VLMs) have remarkable abilities in generating multimodal reasoning tasks. However, potential misuse or safety alignment concerns of VLMs have increased significantly due to different categories of attack vectors.…

End-to-end autonomous driving has emerged as a promising approach to unify perception, prediction, and planning within a single framework, reducing information loss and improving adaptability. However, existing methods often rely on fixed…

Human motion generation driven by deep generative models has enabled compelling applications, but the ability of text-to-motion (T2M) models to produce realistic motions from text prompts raises security concerns if exploited maliciously.…

The Large Vision-Language Model (LVLM) integrates computer vision and natural language processing techniques, offering substantial application potential. However, these models demand extensive resources during inference. Adaptive attention…