Recent text-to-image models have achieved impressive results in generating high-quality images. However, when tasked with multi-concept generation creating images that contain multiple characters or objects, existing methods often suffer from semantic entanglement, including concept entanglement and improper attribute binding, leading to significant text-image inconsistency. We identify that semantic entanglement arises when certain regions of the latent features attend to incorrect concept and attribute tokens. In this work, we propose the Semantic Protection Diffusion Model (SPDiffusion) to address both concept entanglement and improper attribute binding using only a text prompt as input. The SPDiffusion framework introduces a novel concept region extraction method SP-Extraction to resolve region entanglement in cross-attention, along with SP-Attn, which protects concept regions from the influence of irrelevant attributes and concepts. To evaluate our method, we test it on existing benchmarks, where SPDiffusion achieves state-of-the-art results, demonstrating its effectiveness.
Flux-Guard: Facial Identity Protection using diffusion models
School of Cyberspace Security, Beijing University of Posts and Telecommunications(北京邮电大学网络空间安全学院);Nanjing University of Aeronautics and Astronautics(南京航空航天大学)
Beyond Pixels: Semantic-aware Typographic Attack for Geo-Privacy Protection
Hangzhou Institute of Technology, Xidian University, China(杭州科技学院,西安电子科技大学,中国);National University of Singapore(新加坡国立大学);Nanyang Technological University(南洋理工大学);Nankai University(南开大学);New York University(纽约大学);East China Normal University(华东师范大学);Hikvision Digital Technology Co., Ltd(海康威视数字技术有限公司);Shanghai Industrial Control Safety Innovation Tech. Co., Ltd(上海工业控制安全创新技术有限公司)
DIVER: Diving Deeper into Distilled Data via Expressive Semantic Recovery
University of Electronic Science and Technology of China, Chengdu, China(电子科技大学,成都,中国);Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore(高性能计算研究所(IHPC),科技研究局(A*STAR),新加坡);Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research (A*STAR), Singapore(前沿人工智能研究中心(CFAR),科技研究局(A*STAR),新加坡)
Anti-Diffusion: Preventing Abuse of Modifications of Diffusion-Based Models
University of Macau(澳门大学);Shenzhen Institute of Advanced Technology(深圳先进技术研究院);Kuaishou Technology(快手科技);Macau University of Science and Technology(澳门科技大学)
Echoes of ownership: Adversarial-guided dual injection for copyright protection in MLLMs
School of Information Science and Engineering, Lanzhou University(兰州大学信息科学与工程学院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院)
Hierarchical Perceptual Noise Injection for Social Media Fingerprint Privacy Protection
Beihang University(北京航空航天大学);Beijing Advanced Innovation Center for Big Data-Based Precision Medicine(北京大数据精准医疗高精尖创新中心);Wuhan University(武汉大学);JD Explore Academy(京东探索研究院);The University of Sydney(悉尼大学)
GeoCloak: An Agentic Framework for Semantics-Preserving Geolocation Privacy via Peripheral Clue Manipulation
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Hong Kong University of Science and Technology(香港科技大学);CISPA Helmholtz Center for Information Security(CISPA赫尔姆霍兹信息安全中心)
Diffusion-based Adversarial Identity Manipulation for Facial Privacy Protection
School of Computer Science;Engineering, Sun Yat-sen University Guangzhou China;State Key Laboratory of Mathematical Engineering;Engineering, Sun Yat-sen University
SIDeR: Semantic Identity Decoupling for Unrestricted Face Privacy
School of Computer and Information Engineering, Xiamen University of Technology(厦门理工学院计算机与信息工程学院);Department of Electrical and Electronic Engineering, University of Hong Kong(香港大学电子与电气工程系);School of Computer Science, Engineering Research Center of Machine Learning and Industry Intelligence, Sichuan University(四川大学计算机科学学院,机器学习与工业智能工程研究中心);Department of Computer Science, City University of Hong Kong(香港城市大学计算机科学系);College of Artificial Intelligence, Southwest University(西南大学人工智能学院);School of Computer Science, Fudan University(复旦大学计算机科学学院);Department of Computer and Information Science, Faculty of Science and Technology, University of Macau(澳门大学科技学院计算机与信息科学系);Data61, CSIRO(CSIRO Data61);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院)
Collaborative Semantic Aggregation and Calibration for Federated Domain Generalization
Zhejiang University(浙江大学);Key Laboratory for Corneal Diseases Research of Zhejiang Province(浙江省角膜病研究重点实验室);Shanghai Institute for Advanced Study of Zhejiang University(浙江大学上海高等研究院);Shanghai AI Laboratory(上海人工智能实验室)
StegaFFD: Privacy-Preserving Face Forgery Detection via Fine-Grained Steganographic Domain Lifting
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Future Technology, University of Chinese Academy of Sciences(中国科学院大学未来技术学院);Beihang University(北京航空航天大学);Macau University of Science and Technology(澳门科技大学);Nanyang Technological University(南洋理工大学)