中文
相关论文

相关论文: PROBE: Diagnosing Residual Concept Capacity in Era…

200 篇论文

Text-to-Image models such as Stable Diffusion have shown impressive image generation synthesis, thanks to the utilization of large-scale datasets. However, these datasets may contain sexually explicit, copyrighted, or undesirable content,…

计算机视觉与模式识别 · 计算机科学 2023-12-21 Seunghoo Hong , Juhun Lee , Simon S. Woo

Large-scale text-to-image (T2I) diffusion models deliver remarkable visual fidelity but pose safety risks due to their capacity to reproduce undesirable content, such as copyrighted ones. Concept erasure has emerged as a mitigation…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Hoigi Seo , Byung Hyun Lee , Jaehyun Cho , Sungjin Lim , Se Young Chun

Motivated by recent advancements in text-to-image diffusion, we study erasure of specific concepts from the model's weights. While Stable Diffusion has shown promise in producing explicit or realistic artwork, it has raised concerns…

计算机视觉与模式识别 · 计算机科学 2023-06-22 Rohit Gandikota , Joanna Materzynska , Jaden Fiotto-Kaufman , David Bau

Recent success of text-to-image (T2I) generation and its increasing practical applications, enabled by diffusion models, require urgent consideration of erasing unwanted concepts, e.g., copyrighted, offensive, and unsafe ones, from the…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Yuan Wang , Ouxiang Li , Tingting Mu , Yanbin Hao , Kuien Liu , Xiang Wang , Xiangnan He

Text-to-image diffusion models have demonstrated remarkable capabilities in generating high-quality images, yet their tendency to reproduce undesirable concepts, such as NSFW content, copyrighted styles, or specific objects, poses growing…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Zhiqi Zhang , Xinhao Zhong , Yi Sun , Shuoyang Sun , Bin Chen , Shu-Tao Xia , Xuan Wang

Text-to-image diffusion models (DMs) inadvertently reproduce copyrighted styles and protected visual concepts, raising legal and ethical concerns. Concept erasure has emerged as a safeguard, aiming to selectively suppress such concepts…

计算机视觉与模式识别 · 计算机科学 2025-09-29 Jiaqi Liu , Lan Zhang , Xiaoyong Yuan

Concept erasure in text-to-image diffusion models aims to disable pre-trained diffusion models from generating images related to a target concept. To perform reliable concept erasure, the properties of robustness and locality are desirable.…

计算机视觉与模式识别 · 计算机科学 2024-07-19 Chi-Pin Huang , Kai-Po Chang , Chung-Ting Tsai , Yung-Hsuan Lai , Fu-En Yang , Yu-Chiang Frank Wang

Erasing specific concepts from text-to-image diffusion models is essential for avoiding the generation of copyrighted and explicit content. Closed-form concept erasure methods offer a fast alternative to backpropagation-based techniques,…

机器学习 · 计算机科学 2026-05-12 Nicola Novello , Andrea M. Tonello

Concept erasure techniques have recently gained significant attention for their potential to remove unwanted concepts from text-to-image models. While these methods often demonstrate promising results in controlled settings, their…

Large-scale text-to-image (T2I) diffusion models have revolutionized image generation, enabling the synthesis of highly detailed visuals from textual descriptions. However, these models may inadvertently generate inappropriate content, such…

计算机视觉与模式识别 · 计算机科学 2025-03-24 Huiqiang Chen , Tianqing Zhu , Linlin Wang , Xin Yu , Longxiang Gao , Wanlei Zhou

Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. However, the advancement of T2I diffusion models presents significant risks, as the models could be…

计算机视觉与模式识别 · 计算机科学 2025-08-21 Jie Ren , Kangrui Chen , Yingqian Cui , Shenglai Zeng , Hui Liu , Yue Xing , Jiliang Tang , Lingjuan Lyu

Text-to-image generative models can produce photo-realistic images for an extremely broad range of concepts, and their usage has proliferated widely among the general public. On the flip side, these models have numerous drawbacks, including…

机器学习 · 计算机科学 2023-10-10 Minh Pham , Kelly O. Marshall , Niv Cohen , Govind Mittal , Chinmay Hegde

Recent text-to-image (T2I) diffusion and flow-matching models can produce highly realistic images from natural language prompts. In practical scenarios, T2I systems are often run in a ``generate--then--select'' mode: many seeds are sampled…

计算机视觉与模式识别 · 计算机科学 2026-03-05 Huanlei Guo , Hongxin Wei , Bingyi Jing

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…

Recent advances in text-to-image diffusion models have demonstrated remarkable generation capabilities, yet they raise significant concerns regarding safety, copyright, and ethical implications. Existing concept erasure methods address…

计算机视觉与模式识别 · 计算机科学 2026-04-02 Yi Sun , Xinhao Zhong , Hongyan Li , Yimin Zhou , Junhao Li , Bin Chen , Xuan Wang

While modern generative models such as diffusion-based architectures have enabled impressive creative capabilities, they also raise important safety and ethical risks. These concerns have led to growing interest in concept erasure, the…

机器学习 · 计算机科学 2026-04-14 Chi Zhang , Jingpu Cheng , Zhixian Wang , Ping Liu

Text-to-image diffusion models have made significant advancements in generating high-quality, diverse images from text prompts. However, the inherent limitations of textual signals often prevent these models from fully capturing specific…

计算机视觉与模式识别 · 计算机科学 2025-03-19 Ziqiang Li , Jun Li , Lizhi Xiong , Zhangjie Fu , Zechao Li

Concept erasure aims to selectively unlearning undesirable content in diffusion models (DMs) to reduce the risk of sensitive content generation. As a novel paradigm in concept erasure, most existing methods employ adversarial training to…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Qinghong Yin , Yu Tian , Heming Yang , Xiang Chen , Xianlin Zhang , Xueming Li , Yue Zhan

Diffusion models have demonstrated remarkable image generation capabilities, but also pose risks in privacy and fairness by memorizing sensitive concepts or perpetuating biases. We propose a novel \textbf{concept erasure} method for…

计算机视觉与模式识别 · 计算机科学 2025-07-17 Zixuan Fu , Yan Ren , Finn Carter , Chenyue Wang , Ze Niu , Dacheng Yu , Emily Davis , Bo Zhang

While large-scale text-to-image diffusion models have demonstrated impressive image-generation capabilities, there are significant concerns about their potential misuse for generating unsafe content, violating copyright, and perpetuating…

计算机视觉与模式识别 · 计算机科学 2024-05-30 Ruchika Chavhan , Da Li , Timothy Hospedales