相关论文: VisualDAN: Exposing Vulnerabilities in VLMs with V…

Current image generation models can effortlessly produce high-quality, highly realistic images, but this also increases the risk of misuse. In various Text-to-Image or Image-to-Image tasks, attackers can generate a series of images…

Vision-Language Models (VLMs) face significant safety vulnerabilities from malicious prompt attacks due to weakened alignment during visual integration. Existing defenses suffer from efficiency and robustness. To address these challenges,…

Multimodal Large Language Models (MLLMs) are vulnerable to jailbreak attacks, which can elicit harmful responses from MLLMs. Many MLLMs support multi-image inputs, inadvertently introducing new vulnerabilities due to less efforts on…

Vision-Language Models (VLMs), with their strong reasoning and planning capabilities, are widely used in embodied decision-making (EDM) tasks in embodied agents, such as autonomous driving and robotic manipulation. Recent research has…

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 understanding and reasoning tasks. Compared to traditional…

Vision-Language Models (VLMs) combine visual and textual understanding, rendering them well-suited for diverse tasks like generating image captions and answering visual questions across various domains. However, these capabilities are built…

The emergence of vision language models (VLMs) comes with increased safety concerns, as the incorporation of multiple modalities heightens vulnerability to attacks. Although VLMs can be built upon LLMs that have textual safety alignment, it…

Large vision-language models (LVLMs) integrate visual information into large language models, showcasing remarkable multi-modal conversational capabilities. However, the visual modules introduces new challenges in terms of robustness for…

Vision-language models (VLMs) extend large language models (LLMs) with vision encoders, enabling text generation conditioned on both images and text. However, this multimodal integration expands the attack surface by exposing the model to…

Recent years have witnessed remarkable progress in developing Vision-Language Models (VLMs) capable of processing both textual and visual inputs. These models have demonstrated impressive performance, leading to their widespread adoption in…

Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the…

Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them vulnerable to prompt injection attacks. Existing prompt injection methods predominantly…

Multimodal large language models (MLLMs) have become integral to a wide range of real-world applications by jointly reasoning over text and visual inputs. However, despite recent advances in safety alignment, MLLMs remain vulnerable to…

Visual Language Models (VLMs) are vulnerable to adversarial attacks, especially those from adversarial images, which is however under-explored in literature. To facilitate research on this critical safety problem, we first construct a new…

Multimodal large language models (MLLMs) enable powerful cross-modal reasoning capabilities. However, the expanded input space introduces new attack surfaces. Previous jailbreak attacks often inject malicious instructions from text into…

Video-Language Models (VLMs) have demonstrated impressive multi-modal reasoning capabilities across diverse computer vision applications. However, these VLMs are task-specific and assume that both video and language inputs are complete.…

Vision Language Action (VLA) models close the perception action loop by translating multimodal instructions into executable behaviors, but this very capability magnifies safety risks: jailbreaks that merely yield toxic text in LLMs can…

Vision-Language Models (VLMs) excel in generating textual responses from visual inputs, but their versatility raises security concerns. This study takes the first step in exposing VLMs' susceptibility to data poisoning attacks that can…

Large Language Models (LLMs) and Vision-Language Models (VLMs) are increasingly deployed in robotic environments but remain vulnerable to jailbreaking attacks that bypass safety mechanisms and drive unsafe or physically harmful behaviors in…

This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models (LLMs) and Vision-Language Models (VLMs), emphasizing that jailbreak vulnerabilities stem from structural factors such as incomplete training…