相关论文: NutVLM: A Self-Adaptive Defense Framework against …

Safety, security, and compliance are essential requirements when aligning large language models (LLMs). However, many seemingly aligned LLMs are soon shown to be susceptible to jailbreak attacks. These attacks aim to circumvent the models'…

Recent advancements in language-grounded autonomous driving have been significantly promoted by the sophisticated cognition and reasoning capabilities of large language models (LLMs). However, current LLM-based approaches encounter critical…

Multimodal large language models (MLLMs), which bridge the gap between audio-visual and natural language processing, achieve state-of-the-art performance on several audio-visual tasks. Despite the superior performance of MLLMs, the scarcity…

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…

With the widespread adoption and deployment of autonomous driving, handling complex environments has become an unavoidable challenge. Due to the scarcity and diversity of extreme scenario datasets, current autonomous driving models struggle…

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…

Large Vision-Language Models (LVLMs) have achieved impressive progress across various applications but remain vulnerable to malicious queries that exploit the visual modality. Existing alignment approaches typically fail to resist malicious…

Large pre-trained vision-language models (VLMs) offer a promising approach to leveraging human language for enhancing downstream tasks. However, VLMs such as CLIP face significant limitation: its performance is highly sensitive to prompt…

Vision-language models (VLMs) are essential for contextual understanding of both visual and textual information. However, their vulnerability to adversarially manipulated inputs presents significant risks, leading to compromised outputs and…

Prompt injection attacks pose a significant challenge to the safe deployment of Large Language Models (LLMs) in real-world applications. While prompt-based detection offers a lightweight and interpretable defense strategy, its effectiveness…

Machine learning with deep neural networks (DNNs) has become one of the foundation techniques in many safety-critical systems, such as autonomous vehicles and medical diagnosis systems. DNN-based systems, however, are known to be vulnerable…

Vision-Language Models (VLMs) have recently emerged as a promising paradigm in autonomous driving (AD). However, current performance evaluation protocols for VLM-based AD systems (ADVLMs) are predominantly confined to open-loop settings…

The advancement of autonomous driving technologies necessitates increasingly sophisticated methods for understanding and predicting real-world scenarios. Vision language models (VLMs) are emerging as revolutionary tools with significant…

In this paper, we introduce VisioPath, a novel framework combining vision-language models (VLMs) with model predictive control (MPC) to enable safe autonomous driving in dynamic traffic environments. The proposed approach leverages a…

Autonomous vehicles (AVs) are more vulnerable to network attacks due to the high connectivity and diverse communication modes between vehicles and external networks. Deep learning-based Intrusion detection, an effective method for detecting…

Adversarial attacks have emerged as a critical threat to autonomous driving systems. These attacks exploit the underlying neural network, allowing small, almost invisible, perturbations to alter the behavior of such systems in potentially…

Vision-Language Models (VLMs) extend the capabilities of Large Language Models (LLMs) by incorporating visual information, yet they remain vulnerable to jailbreak attacks, especially when processing noisy or corrupted images. Although…

With the rapid advancement of Large Vision-Language Models (LVLMs), ensuring their safety has emerged as a crucial area of research. This survey provides a comprehensive analysis of LVLM safety, covering key aspects such as attacks,…

Test-time adaptation paradigm provides flexibility towards domain shifts by performing immediate adaptation on unlabeled target data from the source model. Vision-Language Models (VLMs) leverage their generalization capabilities for diverse…

Many networking tasks now employ deep learning (DL) to solve complex prediction and optimization problems. However, current design philosophy of DL-based algorithms entails intensive engineering overhead due to the manual design of deep…