Related papers: Not Just Text: Uncovering Vision Modality Typograp…

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…

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…

Multi-Modal Language Models (MLLMs) have transformed artificial intelligence by combining visual and text data, making applications like image captioning, visual question answering, and multi-modal content creation possible. This ability to…

Current Cross-Modality Generation Models (GMs) demonstrate remarkable capabilities in various generative tasks. Given the ubiquity and information richness of vision modality inputs in real-world scenarios, Cross-Vision tasks, encompassing…

The emergence of Vision Language Models (VLMs) is a significant advancement in integrating computer vision with Large Language Models (LLMs) to produce detailed text descriptions based on visual inputs, yet it introduces new security…

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…

Text-to-image generation models have recently attracted unprecedented attention as they unlatch imaginative applications in all areas of life. However, developing such models requires huge amounts of data that might contain…

Vision-Language Models (VLMs) have garnered significant attention for their remarkable ability to interpret and generate multimodal content. However, securing these models against jailbreak attacks continues to be a substantial challenge.…

Text-to-image diffusion models have been widely adopted in real-world applications due to their ability to generate realistic images from textual descriptions. However, recent studies have shown that these methods are vulnerable to backdoor…

Modifying characters of a piece of text to their visual similar ones often ap-pear in spam in order to fool inspection systems and other conditions, which we regard as a kind of adversarial attack to neural models. We pro-pose a way of…

Text-based machine learning models are vulnerable to an emerging class of Unicode-based adversarial examples capable of tricking a model into misreading text with potentially disastrous effects. The primary existing defense against these…

As audio-visual multi-modal large language models (MLLMs) are increasingly deployed in safety-critical applications, understanding their vulnerabilities is crucial. To this end, we introduce Multi-Modal Typography, a systematic study…

The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs. This paper investigates the novel challenge of defending MLLMs against such…

Text-to-Image generation models have revolutionized the artwork design process and enabled anyone to create high-quality images by entering text descriptions called prompts. Creating a high-quality prompt that consists of a subject and…

Text-to-image generative models are widely deployed in creative tools and online platforms. To mitigate misuse, these systems rely on safety filters and moderation pipelines that aim to block harmful or policy violating content. In this…

Typographic attacks exploit the interplay between text and visual content in multimodal foundation models, causing misclassifications when misleading text is embedded within images. Existing datasets are limited in size and diversity,…

In the past years, we have witnessed the remarkable success of Text-to-Image (T2I) models and their widespread use on the web. Extensive research in making T2I models produce hyper-realistic images has led to new concerns, such as…

State-of-the-art Diffusion Models (DMs) produce highly realistic images. While prior work has successfully mitigated Not Safe For Work (NSFW) content in the visual domain, we identify a novel threat: the generation of NSFW text embedded…

Malicious or manipulated prompts are known to exploit text-to-image models to generate unsafe images. Existing studies, however, focus on the passive exploitation of such harmful capabilities. In this paper, we investigate the proactive…

In recent years, Text-to-Image (T2I) models have seen remarkable advancements, gaining widespread adoption. However, this progress has inadvertently opened avenues for potential misuse, particularly in generating inappropriate or…