相关论文: Reading Between the Pixels: Linking Text-Image Emb…

Typographic prompt injection exploits vision language models' (VLMs) ability to read text rendered in images, posing a growing threat as VLMs power autonomous agents. Prior work typically focus on maximizing attack success rate (ASR) but…

Large language models have become increasingly prominent, also signaling a shift towards multimodality as the next frontier in artificial intelligence, where their embeddings are harnessed as prompts to generate textual content.…

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…

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…

Typographic attacks, adding misleading text to images, can deceive vision-language models (LVLMs). The susceptibility of recent large LVLMs like GPT4-V to such attacks is understudied, raising concerns about amplified misinformation in…

Vision-language models (VLMs) have revolutionized multimodal AI applications but introduce novel security vulnerabilities that remain largely unexplored. We present the first comprehensive study of steganographic prompt injection attacks…

Vision-Language Models (VLMs) have witnessed a surge in both research and real-world applications. However, as they are becoming increasingly prevalent, ensuring their robustness against adversarial attacks is paramount. This work…

Large Vision-Language Models (LVLMs) rely on vision encoders and Large Language Models (LLMs) to exhibit remarkable capabilities on various multi-modal tasks in the joint space of vision and language. However, typographic attacks, which…

Recently, there has been a surge of interest in integrating vision into Large Language Models (LLMs), exemplified by Visual Language Models (VLMs) such as Flamingo and GPT-4. This paper sheds light on the security and safety implications of…

Large Vision-Language Models (LVLMs) are susceptible to typographic attacks, which are misclassifications caused by an attack text that is added to an image. In this paper, we introduce a multi-image setting for studying typographic…

Despite inheriting security measures from underlying language models, Vision-Language Models (VLMs) may still be vulnerable to safety alignment issues. Through empirical analysis, we uncover two critical findings: scenario-matched images…

With the rapid advancement of multimodal learning, pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capacities in bridging the gap between visual and language modalities. However, these models remain…

We introduce new jailbreak attacks on vision language models (VLMs), which use aligned LLMs and are resilient to text-only jailbreak attacks. Specifically, we develop cross-modality attacks on alignment where we pair adversarial images…

3D Vision-Language Models (VLMs), such as PointLLM and GPT4Point, have shown strong reasoning and generalization abilities in 3D understanding tasks. However, their adversarial robustness remains largely unexplored. Prior work in 2D VLMs…

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…

With the remarkable success of Vision-Language Models (VLMs) on multimodal tasks, concerns regarding their deployment efficiency have become increasingly prominent. In particular, the number of tokens consumed during the generation process…

Recent advancements in Large Vision-Language Models (VLMs) have underscored their superiority in various multimodal tasks. However, the adversarial robustness of VLMs has not been fully explored. Existing methods mainly assess robustness…

Deploying large vision-language models (LVLMs) introduces a unique vulnerability: susceptibility to malicious attacks via visual inputs. However, existing defense methods suffer from two key limitations: (1) They solely focus on textual…

Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities. However, these models remain highly vulnerable to adversarial attacks. While existing research has primarily focused on…

Large pre-trained Vision Language Models (VLMs) demonstrate excellent generalization capabilities but remain highly susceptible to adversarial examples, posing potential security risks. To improve the robustness of VLMs against adversarial…