检索结果-内蒙古大学图书馆

2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025

作者： Choi, DaEun Son, Kihoon Jung, HyunJoon Kim, Juho School of Computing KAIST Daejeon Korea Republic of Adobe San JoseCA United States

ISBN: (纸本)9798400713958

Broad exploration of references is critical in the visual design process. While text-to-image (T2I) models offer efficiency and customization of exploration, they often limit support for divergence in exploration. We conducted a formative study (N=6) to investigate the limitations of current interaction with the T2I model for broad exploration and found that designers struggle to articulate exploratory intentions and manage iterative, non-linear workflows. To address these challenges, we developed Expandora. Users can specify their exploratory intentions and desired diversity levels through structured input, and using an LLM-based pipeline, Expandora generates tailored prompt variations. The results are displayed in a mindmap-like interface that encourages non-linear workflows. A user study (N=8) demonstrated that Expandora significantly increases prompt diversity, the number of prompts users tried within a given time, and user satisfaction compared to the baseline. Nonetheless, its limitations in supporting convergent thinking suggest opportunities for holistically improving creative processes. © 2025 Copyright held by the owner/author(s).

关键词： Creativity Supporting Tool Design Exploration Generative AI text-to-image model

来源：评论

学校读者我要写书评

暂无评论

AI-supported Nishijin-ori: connecting a text-to-image model to traditional Nishijin-ori textile production 23

AI-supported Nishijin-ori: connecting a text-to-image model ...

引用

2023 SIGGRAPH Asia Posters, SA 2023

作者： Adachi, Asahi Sinapayen, Lana Fukuoka, Hironori Rekimoto, Jun Sony Computer Science Laboratories Nara Institute of Science and Technology Kyoto Japan Sony Computer Science Laboratories National Institute for Basic Biology Kyoto Japan Fukuoka Weaving Co. Ltd. Japan Sony Computer Science Laboratories The University of Tokyo Kyoto Japan

No abstract available.

ISBN: (纸本)9798400703133

No abstract available.

关键词： Geometric patterns Nishijin-ori text-to-image model textiles

来源：评论

学校读者我要写书评

暂无评论

Watermark Removal Attack Against text-to-image Generative model Watermarking

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 1470-1474页

作者： Yuan, Zihan Li, Li Wang, Zichi Jiang, Jingyuan Zhang, Xinpeng Shanghai Univ Sch Commun & Informat Engn Shanghai 200444 Peoples R China

The artist's style can be quickly imitated by fine-tuning a text-to-image model using artist's artworks, which raises serious copyright concerns. Scholars have proposed many watermarking methods to protect the artists' copyright. To evaluate the security and enhance the performance of existing watermarking, this paper proposes a watermark removal attack for text-to-image generative model watermarking for the first time. This attack aims to invalidate watermarking designed to detect art theft mimicry in text-to-image models. In this method, a watermark recognition network and a watermark removal network are designed. The watermark recognition network identifies whether an artwork contains watermark, and the watermark removal network is used to remove it. Consequently, text-to-image models fine-tuned with watermark-removed artworks can reproduce an artist's style while evading watermark detection. This makes the copyright authentication of artworks ineffective. Experiments show that the proposed attack can effectively remove watermarks, with watermark extraction accuracy dropping below 48.64%. Additionally, the images after watermark removal retain high similarity to the original images, with PSNR exceeding 27.96 and SSIM exceeding 0.92.

关键词： Watermarking text to image Accuracy image recognition Training Data mining Discrete wavelet transforms Neural networks Diffusion models Tuning Watermark removal attack text-to-image model model watermarking deep learning

来源：评论

学校读者我要写书评

暂无评论

modeling by Clipped Furniture Parts: Design with text-image model with Stability Understanding 24

Modeling by Clipped Furniture Parts: Design with Text-Image ...

引用

ACM International Conference on Interactive Media Experiences (IMX)

作者： Yoshida, Hironori Itoh, Seiji Future Univ Hakodate Hakodate Hokkaido Japan

ISBN: (纸本)9798400705038

text input in MR(Mixed Reality) provides options for users to model in details instead of just placing objects, however, 3D modeling with text input costs computation and takes time. To overcome this hurdle, we let the text-image model judge 3D layout of furniture parts. Since vanilla text-image model can not judge furniture stability, we tested two approaches: 1. combine with geometric loss, and 2. fne-tuning the model. We report the comparison of these two approaches and discuss further development for MR integration of our system.

关键词： text-to-image model 3D modeling Furniture Design

来源：评论

学校读者我要写书评

暂无评论

Concept Weaver: Enabling Multi-Concept Fusion in text-to-image models

Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Ima...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Kwon, Gihyun Jenni, Simon Li, Dingzeyu Lee, Joon-Young Ye, Jong Chul Heilbron, Fabian Caba Korea Adv Inst Sci & Technol Daejeon South Korea Adobe San Jose CA 95110 USA

ISBN: (纸本)9798350353013;9798350353006

While there has been significant progress in customizing text-to-image generation models, generating images that combine multiple personalized concepts remains challenging. In this work, we introduce Concept Weaver, a method for composing customized text-to-image diffusion models at inference time. Specifically, the method breaks the process into two steps: creating a template image aligned with the semantics of input prompts, and then personalizing the template using a concept fusion strategy. The fusion strategy incorporates the appearance of the target concepts into the template image while retaining its structural details. The results indicate that our method can generate multiple custom concepts with higher identity fidelity compared to alternative approaches. Furthermore, the method is shown to seamlessly handle more than two concepts and closely follow the semantic meaning of the input prompt without blending appearances across different subjects.

关键词： Custom Concept Diffusion model Multi-concept Personalization text-to-image model

来源：评论

学校读者我要写书评

暂无评论

SafeGen: Mitigating Sexually Explicit Content Generation in text-to-image models 24

SafeGen: Mitigating Sexually Explicit Content Generation in ...

引用

31st Conference on Computer and Communications Security

作者： Li, Xinfeng Yang, Yuchen Deng, Jiangyi Yan, Chen Chen, Yanjiao Ji, Xiaoyu Xu, Wenyuan Zhejiang Univ Hangzhou Zhejiang Peoples R China Johns Hopkins Univ Baltimore MD USA

ISBN: (纸本)9798400706363

text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years. However, text-to-image models may be tricked into generating not-safe-for-work (NSFW) content, particularly in sexually explicit scenarios. Existing countermeasures mostly focus on filtering inappropriate inputs and outputs, or suppressing improper text embeddings, which can block sexually explicit content (e.g., naked) but may still be vulnerable to adversarial prompts-inputs that appear innocent but are ill-intended. In this paper, we present SafeGen, a framework to mitigate sexual content generation by text-to-image models in a text-agnostic manner. The key idea is to eliminate explicit visual representations from the model regardless of the text input. In this way, the text-to-image model is resistant to adversarial prompts since such unsafe visual representations are obstructed from within. Extensive experiments conducted on four datasets and large-scale user studies demonstrate SafeGen's effectiveness in mitigating sexually explicit content generation while preserving the high-fidelity of benign images. SafeGen outperforms eight state-of-the-art baseline methods and achieves 99.4% sexual content removal performance.

关键词： text-to-image model Sexually Explicit Safety Unsafe Mitigation

来源：评论

学校读者我要写书评

暂无评论

Identical Human Preference Alignment Paradigm for text-to-image models

Identical Human Preference Alignment Paradigm for Text-to-Im...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Sun, Haoyuan Xia, Bo Zhao, Yifei Chang, Yongzhe Wang, Xueqian Shenzhen International Graduate School Tsinghua University Shenzhen China

ISBN: (纸本)9798350368741

Implicit reward mechanism of Direct Preference Optimization (DPO) has facilitated its recent applications beyond large language models (LLMs), notably in aligning text-to-image models with human preferences. While promising results have been achieved with algorithms such as Diffusion-DPO, their reliance on the assumptions of the Bradley-Terry model could potentially lead to significant overfitting. In this paper, we propose the Step Identical Preference Alignment (SIPA) method, departing text-to-image alignment from the assumptions of Bradley-Terry preference model. We assess the performance of four models, Diffusion-DPO, SPO, and SIPA, alongside the original model, on the HPS-V2 test set, which focus on three key aspects: text-image alignment, human value alignment, and generation diversity. Experimental results show that SIPA matches or outperforms existing SOTA alignment methods, and even exceeds the original model in terms of generation diversity, which compellingly demonstrates SIPA's superiority in mitigating alignment overfitting. © 2025 IEEE.

关键词： human preference alignment preference modeling text-to-image model

来源：评论

学校读者我要写书评

暂无评论

Customizable text-to-image modeling by Contrastive Learning on Adjustable Word-Visual Pairs 3rd

Customizable Text-to-Image Modeling by Contrastive Learning ...

引用

3rd International Conference on Artificial Intelligence in HCI (AI-HCI) Held as Part of the 24th International Conference on Human-Computer Interaction (HCII)

作者： Lu, Jun-Li Ochiai, Yoichi Univ Tsukuba Res & Dev Ctr Digital Nat Tsukuba Ibaraki Japan Univ Tsukuba Fac Lib Informat & Media Sci Tsukuba Ibaraki Japan

ISBN: (纸本)9783031056437;9783031056420

Co-creation with AI is trending and AI-generation of images from textual descriptions has shown advanced and attractive capabilities. However, commonly trained machine-learning models or built AI-based systems may have deficient points to generate satisfied results for personal usage or novice users of painting or AI co-creation, maybe because of deficient understanding of personal textual expressions or low customization of trained text-to-image machine learning models. Therefore, we assist in creating flexible and diverse visual contents from textual descriptions, by developing neural-networks models with machine learning. In modeling, we generate synthesized images using word-visual co-occurrence by Transformer model and synthesize images by decoding visual tokens. To improve visual and textual expressions and their relevance with more diversities, we utilize contrastive learning applying on texts, images, or pairs of texts and images. In the experimental results of a dataset of birds, we showed that the rendering quality was required of models with some scale neural-networks, and necessary training process with fined training by applying relatively low learning rates until the end of training. We further showed contrastive learning was possible for improvement of visual and textual expressions and their relevance.

关键词： AI visual content creation text-to-image model Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Adversarial attacks and defenses on text-to-image diffusion models: A survey

引用

INFORMATION FUSION 2025年 114卷

作者： Zhang, Chenyu Hu, Mingwang Li, Wenhui Wang, Lanjun Tianjin Univ Tianjin Peoples R China

Recently, the text-to-image diffusion model has gained considerable attention from the community due to its exceptional image generation capability. A representative model, Stable Diffusion, amassed more than 10 million users within just two months of its release. This surge in popularity has facilitated studies on the robustness and safety of the model, leading to the proposal of various adversarial attack methods. Simultaneously, there has been a marked increase in research focused on defense methods to improve the robustness and safety of these models. In this survey, we provide a comprehensive review of the literature on adversarial attacks and defenses targeting text-to-image diffusion models. We begin with an overview of text-to-image diffusion models, followed by an introduction to a taxonomy of adversarial attacks and an in-depth review of existing attack methods. We then present a detailed analysis of current defense methods that improve model robustness and safety. Finally, we discuss ongoing challenges and explore promising future research directions. For a complete list of the adversarial attack and defense methods covered in this survey, please refer to our curated repository at https://***/datar001/Awesome-AD-on-T2IDM. Warning: This paper includes model-generated content that may contain offensive or distressing material.

关键词： text-to-image model Adversarial machine learning model safety model robustness Review

来源：评论

学校读者我要写书评

暂无评论

Unified Prompt Attack Against text-to-image Generation models

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2025年第6期47卷 4816-4834页

作者： Peng, Duo Ke, Qiuhong Huang, Mark He Hu, Ping Liu, Jun Singapore Univ Technol & Design Singapore 487372 Singapore Monash Univ Clayton Vic 3800 Australia Univ Elect Sci & Technol China Chengdu 610054 Peoples R China Univ Lancaster Lancaster LA1 4YW England

text-to-image (T2I) models have advanced significantly, but their growing popularity raises security concerns due to their potential to generate harmful images. To address these issues, we propose UPAM, a novel framework to evaluate the robustness of T2I models from an attack perspective. Unlike prior methods that focus solely on textual defenses, UPAM unifies the attack on both textual and visual defenses. Additionally, it enables gradient-based optimization, overcoming reliance on enumeration for improved efficiency and effectiveness. To handle cases where T2I models block image outputs due to defenses, we introduce Sphere-Probing Learning (SPL) to enable optimization even without image results. Following SPL, our model bypasses defenses, inducing the generation of harmful content. To ensure semantic alignment with attacker intent, we propose Semantic-Enhancing Learning (SEL) for precise semantic control. UPAM also prioritizes the naturalness of adversarial prompts using In-context Naturalness Enhancement (INE), making them harder for human examiners to detect. Additionally, we address the issue of iterative queries-common in prior methods and easily detectable by API defenders-by introducing Transferable Attack Learning (TAL), allowing effective attacks with minimal queries. Extensive experiments validate UPAM's superiority in effectiveness, efficiency, naturalness, and low query detection rates.

关键词： Optimization Closed box Visualization Training Adaptation models Semantics Security text to image Glass box Electronic mail Adversarial prompt attack text-to-image model closed box gradient-based optimization naturalness

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：