Pretrained diffusion models and their outputs are widely accessible due to their exceptional capacity for synthesizing high-quality images and their open-source nature. The users, however, may face litigation risks owing to the models' tendency to memorize and regurgitate training data during inference. To address this, we introduce Anti-Memorization Guidance (AMG), a novel framework employing three targeted guidance strategies for the main causes of memorization: image and caption duplication, and highly specific user prompts. Consequently, AMG ensures memorization-free outputs while maintaining high image quality and text alignment, leveraging the synergy of its guidance methods, each indispensable in its own right. AMG also features an innovative automatic detection system for potential memorization during each step of inference process, allows selective application of guidance strategies, minimally interfering with the original sampling process to preserve output utility. We applied AMG to pretrained Denoising Diffusion Probabilistic Models (DDPM) and Stable Diffusion across various generation tasks. The results demonstrate that AMG is the first approach to successfully eradicates all instances of memorization with no or marginal impacts on image quality and text-alignment, as evidenced by FID and CLIP scores.
Capacity Control is an Effective Memorization Mitigation Mechanism in Text-Conditional Diffusion Models
School of Informatics, University of Edinburgh(爱丁堡大学信息学院);School of Engineering, University of Edinburgh(爱丁堡大学工程学院);Samsung AI Center, Cambridge(三星剑桥人工智能中心)
Investigating Memorization in Video Diffusion Models
School of Computer Science, Faculty of Engineering, The University of Sydney, Australia(悉尼大学计算机科学学院,工程学院);School of Physics, Mathematics and Computing, The University of Western Australia, Australia(西澳大学物理、数学与计算学院);Center for Research in Computer Vision, University of Central Florida, USA(佛罗里达中央大学计算机视觉研究中心)
Filtering Memorization from Parameter-Space in Diffusion Models
RIKEN AIP(理化学研究所Advanced Institute for Peripheral Research);Science of Tokyo(东京科学大学);University of California, Berkeley(加州大学伯克利分校);Zhejiang University(浙江大学)
Exploring Local Memorization in Diffusion Models via Bright Ending Attention
School of Computer Science, Faculty of Engineering, The University of Sydney, Australia(悉尼大学计算机科学学院、工程学院);School of Physics, Mathematics and Computing, The University of Western Australia, Australia(西澳大学物理、数学与计算学院);Center for Research in Computer Vision, University of Central Florida, USA(佛罗里达中央大学计算机视觉研究中心)
Redistribute Ensemble Training for Mitigating Memorization in Diffusion Models
School of Computer Science, Wuhan University(武汉大学计算机学院);School of Cyber Science and Technology, Sun Yat-sen University(中山大学网络空间科学与技术学院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院)
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);Institute of Microelectronics, Chinese Academy of Sciences(中国科学院微电子研究所)
Demystifying Foreground-Background Memorization in Diffusion Models
Cheriton School of Computer Science, University of Waterloo and Vector Institute(查尔顿计算机科学学院,滑铁卢大学和向量研究所);University of Ottawa(渥太华大学);CISPA Helmholtz Center for Information Security(信息安全赫尔姆霍茨中心CISPA)
Investigating Data Memorization in 3D Latent Diffusion Models for Medical Image Synthesis
Heidelberg University Hospital(海德堡大学医院);German Centre for Cardiovascular Research(德国心血管研究中心);Heidelberg University(海德堡大学);University Medical Center Mannheim(曼海姆大学医学中心)
Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models
School of Computer Science, Faculty of Engineering, The University of Sydney, Australia(悉尼大学计算机科学学院,工程学院);School of Physics, Mathematics and Computing, The University of Western Australia, Australia(西澳大学物理、数学与计算学院);Center for Research in Computer Vision, University of Central Florida, USA(佛罗里达中央大学计算机视觉研究中心)
Unconditional Latent Diffusion Models Memorize Patient Imaging Data: Implications for Openly Sharing Synthetic Data
Heidelberg University Hospital(海德堡大学医院);AI Health Innovation Cluster (AIH)(AI健康创新集群);German Centre for Cardiovascular Research (DZHK)(德国心血管研究中心);University Medical Center Mannheim(曼海姆大学医学中心);University Hospital Aachen(亚琛大学医院);University Hospital Würzburg(维尔茨堡大学医院);University Medical Center Mainz(美因茨大学医学中心);TUD Dresden University of Technology(德累斯顿工业大学);University Hospital Dresden(德累斯顿大学医院);National Center for Tumor Diseases (NCT)(国家肿瘤疾病中心)
Finding DoRI: Discovery of Retained Images in Diffusion Models
CISPA Helmholtz Center for Information Security(CISPA信息安全研究中心);German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心(DFKI));Technical University of Darmstadt(达姆施塔特技术大学);Hessian Center for AI (Hessian.AI)(黑森人工智能中心(Hessian.AI));Centre for Cognitive Science, Technical University of Darmstadt(达姆施塔特技术大学认知科学中心)
Memorization to Generalization: Emergence of Diffusion Models from Associative Memory
Department of Computer Science, Rensselaer Polytechnic Institute ( RPI )(计算机科学系,罗切斯特理工学院(RPI));Jheronimus Academy of Data Science, Tilburg University(数据科学学院,蒂尔堡大学);Department of Physics, University of Rome Sapienza(物理系,罗马萨皮恩扎大学);Donders Institute for Brain, Cognition, and Behaviour, Radboud University(大脑、认知与行为研究所,拉德堡德大学);IBM Research(IBM研究院)
Diffusion Model Meets Non-Exemplar Class-Incremental Learning and Beyond
Beijing National Research Center for Information Science and Technology (BNRist)(北京信息科学与技术国家研究中心(BNRist));Department of Electronic Engineering, Tsinghua University(清华大学电子工程系)
A Probabilistic Fluctuation based Membership Inference Attack for Diffusion Models
School of Cyber Science and Engineering, Huazhong University of Science and Technology(华中科技大学网络空间科学与工程学院);Tsinghua University(清华大学);Dalian University of Technology(大连理工大学)
TTOM: Test-Time Optimization and Memorization for Compositional Video Generation
National University of Singapore(国立新加坡大学);University of Science and Technology of China(中国科学技术大学);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳))
Towards Application Aligned Synthetic Surgical Image Synthesis
Department of Translational Surgical Oncology, NCT/UCC Dresden(转化外科肿瘤学系);DKFZ, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden,HZDR, Germany(德累斯顿技术大学医学院);The Centre for Tactile Internet with Human-in-the-Loop (CeTI), TUD Dresden(人机交互 tactile 网络中心)
Department of Computer Science The University of Texas at Austin(计算机科学系 德克萨斯大学奥斯汀分校);Department of Neuroscience The University of Texas at Austin(神经科学系 德克萨斯大学奥斯汀分校)