Related papers: Attention Hijacking: Response Manipulation Across …

Visual Question Answering (VQA) is a fundamental task in computer vision and natural language process fields. Although the ``pre-training & finetuning'' learning paradigm significantly improves the VQA performance, the adversarial…

Large Vision-Language Models (VLMs) have achieved remarkable success in understanding complex real-world scenarios and supporting data-driven decision-making processes. However, VLMs exhibit significant vulnerability against adversarial…

Black-box adversarial attack on vision-language pre-trained models is a practical and challenging task, as text and image perturbations need to be considered simultaneously, and only the predicted results are accessible. Research on this…

Vision-Language Models (VLMs) are increasingly used in clinical diagnostics, yet their robustness to adversarial attacks remains largely unexplored, posing serious risks. Existing medical attacks focus on secondary objectives such as model…

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…

Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding, such as image captioning and response generation. As the practical applications of vision-language models become…

Vision Large Language Models (VLLMs) are increasingly deployed to offer advanced capabilities on inputs comprising both text and images. While prior research has shown that adversarial attacks can transfer from open-source to proprietary…

Are foundation models secure against malicious actors? In this work, we focus on the image input to a vision-language model (VLM). We discover image hijacks, adversarial images that control the behaviour of VLMs at inference time, and…

Vision-language models (VLMs) seamlessly integrate visual and textual data to perform tasks such as image classification, caption generation, and visual question answering. However, adversarial images often struggle to deceive all prompts…

Recent research suggests that Vision Language Models (VLMs) often rely on inherent biases learned during training when responding to queries about visual properties of images. These biases are exacerbated when VLMs are asked highly specific…

Adversarial attacks have evolved from simply disrupting predictions on conventional task-specific models to the more complex goal of manipulating image semantics on Large Vision-Language Models (LVLMs). However, existing methods struggle…

Large Vision-Language Models (LVLMs) rely on attention-based retrieval of safety instructions to maintain alignment during generation. Existing attacks typically optimize image perturbations to maximize harmful output likelihood, but suffer…

In typical multimodal tasks, such as Visual Question Answering (VQA), adversarial attacks targeting a specific image and question can lead large vision-language models (LVLMs) to provide incorrect answers. However, it is common for a single…

Vision-Language Models (VLMs) have been shown to be blind, often underutilizing their visual inputs even on tasks that require visual reasoning. In this work, we demonstrate that VLMs are selectively blind. They modulate the amount of…

Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal tasks, yet their reliability is persistently undermined by hallucinations-generating text that contradicts visual input. Recent studies often attribute…

Recent research on Vision Language Models (VLMs) suggests that they rely on inherent biases learned during training to respond to questions about visual properties of an image. These biases are exacerbated when VLMs are asked highly…

Vision-language model (VLM) hallucination is commonly linked to imbalanced allocation of attention across input modalities: system, image and text. However, existing mitigation strategies tend towards an image-centric interpretation of…

Vision-Language Models (VLMs) have recently demonstrated remarkable capabilities in comprehending complex visual content. However, the mechanisms underlying how VLMs process visual information remain largely unexplored. In this paper, we…

Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an…

Despite their success, Large Vision-Language Models (LVLMs) remain vulnerable to hallucinations. While existing studies attribute the cause of hallucinations to insufficient visual attention to image tokens, our findings indicate that…