Related papers: Web Artifact Attacks Disrupt Vision Language Model…

This paper develops small vision language models to understand visual art, which, given an art work, aims to identify its emotion category and explain this prediction with natural language. While small models are computationally efficient,…

While vision-language pre-training model (VLP) has shown revolutionary improvements on various vision-language (V+L) tasks, the studies regarding its adversarial robustness remain largely unexplored. This paper studied the adversarial…

The generative capabilities of Large Language Models (LLMs) are rapidly expanding from static code to dynamic, interactive visual artifacts. This progress is bottlenecked by a critical evaluation gap: established benchmarks focus on…

On-device Vision-Language Models (VLMs) promise data privacy via local execution. However, we show that the architectural shift toward Dynamic High-Resolution preprocessing (e.g., AnyRes) introduces an inherent algorithmic side-channel.…

Multi-modal Large Language Models (MLLMs) excel in vision-language tasks but remain vulnerable to visual adversarial perturbations that can induce hallucinations, manipulate responses, or bypass safety mechanisms. Existing methods seek to…

While vision-language models (VLMs) have achieved remarkable performance improvements recently, there is growing evidence that these models also posses harmful biases with respect to social attributes such as gender and race. Prior studies…

Recent video generative models have greatly improved the realism of AI-generated videos, yet their outputs still exhibit artifacts such as temporal inconsistencies, structural distortions, and semantic incoherence. While Multimodal Large…

The widespread use of Vision Language Models (VLMs, e.g. CLIP) has raised concerns about their vulnerability to sophisticated and imperceptible adversarial attacks. These attacks could compromise model performance and system security in…

We present a vision-language model (VLM) that automatically edits website HTML to address violations of the Web Content Accessibility Guidelines 2 (WCAG2) while preserving the original design. We formulate this as a supervised…

Typographic attacks exploit multi-modal systems by injecting text into images, leading to targeted misclassifications, malicious content generation and even Vision-Language Model jailbreaks. In this work, we analyze how CLIP vision encoders…

Large Vision-Language Models (LVLMs) can be vulnerable to adversarial images that subtly bias their outputs toward plausible yet incorrect responses. We introduce a general, efficient, and training-free defense that combines image…

The contemporary phenomenon of deepfakes, utilizing GAN or diffusion models for face swapping, presents a substantial and evolving threat in digital media, identity verification, and a multitude of other systems. The majority of existing…

LLM watermarks stand out as a promising way to attribute ownership of LLM-generated text. One threat to watermark credibility comes from spoofing attacks, where an unauthorized third party forges the watermark, enabling it to falsely…

Vision-language models demand watermarking solutions that protect intellectual property without compromising multimodal coherence. Existing text watermarking methods disrupt visual-textual alignment through biased token selection and static…

Multimodal product retrieval systems in e-commerce platforms rely on effectively combining visual and textual signals to improve search relevance and user experience. However, vision-language models such as CLIP are vulnerable to…

The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision component: (1) encoding harmful instructions as visual symbol…

Adversarial attacks aim to generate malicious inputs that mislead deep models, but beyond causing model failure, they cannot provide certain interpretable information such as ``\textit{What content in inputs make models more likely to…

The Large Vision-Language Model (LVLM) has enhanced the performance of various downstream tasks in visual-language understanding. Most existing approaches encode images and videos into separate feature spaces, which are then fed as inputs…

The success of VLMs often relies on the dynamic high-resolution schema that adaptively augments the input images to multiple crops, so that the details of the images can be retained. However, such approaches result in a large number of…

With Vision-Language Pre-training (VLP) models demonstrating powerful multimodal interaction capabilities, the application scenarios of neural networks are no longer confined to unimodal domains but have expanded to more complex multimodal…