相关论文: Vulnerability of Text-to-Image Models to Prompt Te…

Prompt-guided generative AI models have rapidly expanded across vision and language domains, producing realistic and diverse outputs from textual inputs. The growing variety of such models, trained with different data and architectures,…

Visual-prompt-guided edit transfer aims to learn image transformations directly from example pairs, offering more precise and controllable editing than purely text-driven approaches. However, existing diffusion transformer-based methods…

Large language models (LLMs) have been widely adopted across various applications, leveraging customized system prompts for diverse tasks. Facing potential system prompt leakage risks, model developers have implemented strategies to prevent…

The proliferation of Large Language Models (LLMs) has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and circumvent safety alignments. These prompt-based attacks…

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…

Infostealers exfiltrate credentials, session cookies, and sensitive data from infected systems. With over 29 million stealer logs reported in 2024, manual analysis and mitigation at scale are virtually unfeasible/unpractical. While most…

Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language understanding tasks, yet their inference efficiency is often hampered by the large number of visual tokens, particularly in…

Given the power of vision transformers, a new learning paradigm, pre-training and then prompting, makes it more efficient and effective to address downstream visual recognition tasks. In this paper, we identify a novel security threat…

Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through…

The rapid advancement of generative models has significantly enhanced the realism and customization of digital content creation. The increasing power of these tools, coupled with their ease of access, fuels the creation of photorealistic…

Visual Generative AI models have demonstrated remarkable capability in generating high-quality images from user inputs like text prompts. However, because these models have billions of parameters, they risk memorizing certain parts of the…

In the evolving domain of text-to-image generation, diffusion models have emerged as powerful tools in content creation. Despite their remarkable capability, existing models still face challenges in achieving controlled generation with a…

Recent studies on AI security have highlighted the vulnerability of Vision-Language Pre-training (VLP) models to subtle yet intentionally designed perturbations in images and texts. Investigating multimodal systems' robustness via…

We present a framework for optimizing prompts in vision-language models to elicit multimodal reasoning without model retraining. Using an evolutionary algorithm to guide prompt updates downstream of visual tasks, our approach improves upon…

Today, machine learning is widely applied in sensitive, security-related, and financially lucrative applications. Model extraction attacks undermine current business models where a model owner sells model access, e.g., via MLaaS APIs.…

Speculative decoding is a powerful way to accelerate autoregressive large language models (LLMs), but directly porting it to vision-language models (VLMs) faces unique systems constraints: the prefill stage is dominated by visual tokens…

Text-to-image generation models that generate images based on prompt descriptions have attracted an increasing amount of attention during the past few months. Despite their encouraging performance, these models raise concerns about the…

We propose VisTex-OVLM, a novel image prompted object detection method that introduces visual textualization -- a process that projects a few visual exemplars into the text feature space to enhance Object-level Vision-Language Models'…

Large pre-trained vision-language (VL) models can learn a new task with a handful of examples and generalize to a new task without fine-tuning. However, these VL models are hard to deploy for real-world applications due to their…

The development of unified multimodal large language models (MLLMs) is fundamentally challenged by the granularity gap between visual understanding and generation: understanding requires high-level semantic abstractions, while image…