相关论文: MirrorCheck: Efficient Adversarial Defense for Vis…

Large-scale contrastive pre-training produces powerful Vision-and-Language Models (VLMs) capable of generating representations (embeddings) effective for a wide variety of visual and multimodal tasks. However, these pretrained embeddings…

We propose a visual-linguistic representation learning approach within a self-supervised learning framework by introducing a new operation, loss, and data augmentation strategy. First, we generate diverse features for the image-text…

Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities, yet their proficiency in understanding and reasoning over multiple images remains largely unexplored. While existing benchmarks have initiated the evaluation of…

Vision-Language Models (VLMs) have demonstrated strong capabilities in aligning visual and textual modalities, enabling a wide range of applications in multimodal understanding and generation. While they excel in zero-shot and transfer…

Generative medical vision-language models~(Med-VLMs) are primarily designed to generate complex textual information~(e.g., diagnostic reports) from multimodal inputs including vision modality~(e.g., medical images) and language…

Multimodal Machine Learning systems, particularly those aligning text and image data like CLIP/BLIP models, have become increasingly prevalent, yet remain susceptible to adversarial attacks. While substantial research has addressed…

Recently, large vision-language models (LVLMs) have emerged as the preferred tools for judging text-image alignment, yet their robustness along the visual modality remains underexplored. This work is the first study to address a key…

Retrieval Augmented Language Models (RALMs) have gained significant attention for their ability to generate accurate answer and improve efficiency. However, RALMs are inherently vulnerable to imperfect information due to their reliance on…

Multimodal Large Language Models (MLLMs), are recent advancement of Vision-Language Models (VLMs) that have driven major advances in video understanding. However, their vulnerability to adversarial tampering and manipulations remains…

Vision-Language Models (VLMs) have achieved impressive performance across a wide range of multimodal tasks, yet they often exhibit inconsistent behavior when faced with semantically equivalent inputs, undermining their reliability and…

Achieving adversarial robustness in Vision-Language Models (VLMs) inevitably compromises accuracy on clean data, presenting a long-standing and challenging trade-off. In this work, we revisit this trade-off by investigating a fundamental…

Model inversion (MI) attacks pose significant privacy risks by reconstructing private training data from trained neural networks. While prior studies have primarily examined unimodal deep networks, the vulnerability of vision-language…

Large language models (LLMs) demonstrate general intelligence across a variety of machine learning tasks, thereby enhancing the commercial value of their intellectual property (IP). To protect this IP, model owners typically allow user…

Text-to-image synthesis aims to generate a photo-realistic and semantic consistent image from a specific text description. The images synthesized by off-the-shelf models usually contain limited components compared with the corresponding…

Recent advances in deep learning research have shown remarkable achievements across many tasks in computer vision (CV) and natural language processing (NLP). At the intersection of CV and NLP is the problem of image captioning, where the…

This work investigates a fundamental question: Do Video-Language Models (VidLMs) robustly account for video content, temporal sequence, and motion? Our investigation shows that, surprisingly, they often do not. We introduce REVEAL{}, a…

Recent advances in Large Visual Language Models (LVLMs) have demonstrated impressive performance across various vision-language tasks by leveraging large-scale image-text pretraining and instruction tuning. However, the security…

Text-to-image (T2I) diffusion models (DMs) have shown promise in generating high-quality images from textual descriptions. The real-world applications of these models require particular attention to their safety and fidelity, but this has…

As Large Language Models quickly become ubiquitous, it becomes critical to understand their security vulnerabilities. Recent work shows that text optimizers can produce jailbreaking prompts that bypass moderation and alignment. Drawing from…

Autoregressive language models are vulnerable to orthographic attacks, where input text is perturbed with characters from multilingual alphabets, leading to substantial performance degradation. This vulnerability primarily stems from the…