相关论文: Unified Prompt Attack Against Text-to-Image Genera…

With the increase in cybersecurity vulnerabilities of software systems, the ways to exploit them are also increasing. Besides these, malware threats, irregular network interactions, and discussions about exploits in public forums are also…

Large Vision-Language Models (VLMs) have demonstrated remarkable performance across multimodal tasks by integrating vision encoders with large language models (LLMs). However, these models remain vulnerable to adversarial attacks. Among…

The rapid evolution of text-to-image diffusion models has opened the door of generative AI, enabling the translation of textual descriptions into visually compelling images with remarkable quality. However, a persistent challenge within…

Despite recent advances in diffusion models, top-tier text-to-image (T2I) models still struggle to achieve precise spatial layout control, i.e. accurately generating entities with specified attributes and locations.…

Large language models have become increasingly prominent, also signaling a shift towards multimodality as the next frontier in artificial intelligence, where their embeddings are harnessed as prompts to generate textual content.…

Recently, remarkable progress has been made in Unified Multimodal Models (UMMs), which integrate vision-language generation and understanding capabilities within a single framework. However, a significant gap exists where a model's strong…

Text-to-image models are vulnerable to the stepwise "Divide-and-Conquer Attack" (DACA) that utilize a large language model to obfuscate inappropriate content in prompts by wrapping sensitive text in a benign narrative. To mitigate stepwise…

We introduce Lumina-Image 2.0, an advanced text-to-image generation framework that achieves significant progress compared to previous work, Lumina-Next. Lumina-Image 2.0 is built upon two key principles: (1) Unification - it adopts a…

Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically designed to bypass existing defenses. To address this vulnerability, we propose MirrorCheck, a…

Large-scale pre-trained Vision-Language models (VLMs), such as CLIP, exhibit strong zero-shot generalization, yet remain highly vulnerable to imperceptible adversarial perturbations, raising serious safety concerns for open-world…

Text-to-Image (T2I) generation has achieved remarkable progress in recent years. Meanwhile, reinforcement learning methods, particularly those based on Group Relative Policy Optimization (GRPO), have attracted widespread attention and been…

As large language models have demonstrated impressive performance in many domains, recent works have adopted language models (LMs) as controllers of visual modules for vision-and-language tasks. While existing work focuses on equipping LMs…

Text-guided image manipulation with diffusion models enables flexible and precise editing based on prompts, but raises ethical and copyright concerns due to potential unauthorized modifications. To address this, we propose SecureT2I, a…

The growing demand for customized visual content has led to the rise of personalized text-to-image (T2I) diffusion models. Despite their remarkable potential, they pose significant privacy risk when misused for malicious purposes. In this…

The rise of text-to-image (T2I) models has enabled the synthesis of photorealistic human portraits, raising serious concerns about identity misuse and the robustness of AIGC detectors. In this work, we propose an automated adversarial…

In the text-to-image generation field, recent remarkable progress in Stable Diffusion makes it possible to generate rich kinds of novel photorealistic images. However, current models still face misalignment issues (e.g., problematic spatial…

Despite recent significant strides achieved by diffusion-based Text-to-Image (T2I) models, current systems are still less capable of ensuring decent compositional generation aligned with text prompts, particularly for the multi-object…

Despite recent advances in text-to-image (T2I) models, they often fail to faithfully render all elements of complex prompts, frequently omitting or misrepresenting specific objects and attributes. Test-time optimization has emerged as a…

Text-to-Image (T2I) models have achieved remarkable success in generating visual content from text inputs. Although multiple safety alignment strategies have been proposed to prevent harmful outputs, they often lead to overly cautious…

Neural Image Classifiers are effective but inherently hard to interpret and susceptible to adversarial attacks. Solutions to both problems exist, among others, in the form of counterfactual examples generation to enhance explainability or…