As diffusion probabilistic models (DPMs) become central to Generative AI (GenAI), understanding their memorization behavior is essential for evaluating risks such as data leakage, copyright infringement, and trustworthiness. While prior research finds conditional DPMs highly susceptible to data extraction attacks using explicit prompts, unconditional models are often assumed to be safe. We challenge this view by introducing \textbf{Surrogate condItional Data Extraction (SIDE)}, a general framework that constructs data-driven surrogate conditions to enable targeted extraction from any DPM. Through extensive experiments on CIFAR-10, CelebA, ImageNet, and LAION-5B, we show that SIDE can successfully extract training data from so-called safe unconditional models, outperforming baseline attacks even on conditional models. Complementing these findings, we present a unified theoretical framework based on informative labels, demonstrating that all forms of conditioning, explicit or surrogate, amplify memorization. Our work redefines the threat landscape for DPMs, establishing precise conditioning as a fundamental vulnerability and setting a new, stronger benchmark for model privacy evaluation.
Conditional deep generative models as surrogates for spatial field solution reconstruction with quantified uncertainty in Structural Health Monitoring applications
National Technical University of Athens（雅典国立技术大学）；School of Naval Architecture and Marine Engineering（船舶与海洋工程学院）
Data-driven Full-waveform Inversion Surrogate using Conditional Generative Adversarial Networks
Universidade Federal do Espírito Santo（巴西联邦圣埃斯皮里图大学）；Instituto Federal do Espírito Santo（圣埃斯皮里图联邦理工学院）；Exploração e Produção Petróleo Brasileiro S.A.（巴西国家石油公司勘探与生产部门）
Center for Machine Learning (ZML)（机器学习中心（ZML））；Institute for Flow in Additively Manufactured Porous Structures (ISAPS)（添加剂制造多孔结构流动研究所（ISAPS））；Heilbronn University of Applied Sciences（海德堡应用科学大学）
Toward AI-Driven Digital Twins for Metropolitan Floods: A Conditional Latent Dynamics Network Surrogate of the Shallow Water Equations
School of Computational Science and Engineering, Georgia Institute of Technology（计算科学与工程学院，佐治亚理工学院）；Environmental Science Division, Argonne National Laboratory（环境科学部，阿贡国家实验室）
Conditional neural control variates for variance reduction in Bayesian inverse problems
Department of Computer Science University of Central Florida（计算机科学系佛罗里达中央大学）；Department of Physics and Maryland Center for Fundamental Physics University of Maryland College Park（物理系马里兰根本物理中心马里兰大学学院公园分校）
Towards Spatio-Temporal Extrapolation of Phase-Field Simulations with Convolution-Only Neural Networks
Sandia National Laboratories（桑迪亚国家实验室）；Lawrence Berkeley National Laboratory（伯克利劳伦斯国家实验室）；University of California, Berkeley（加州大学伯克利分校）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）
Boosting Black-Box Attack with Partially Transferred Conditional Adversarial Distribution
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Tencent AI Lab（腾讯人工智能实验室）
Generative Bayesian Computation as a Scalable Alternative to Gaussian Process Surrogates
Booth School of Business, University of Chicago（芝加哥大学商学院）；Department of Systems Engineering and Operations Research, George Mason University（乔治·马歇尔大学系统工程与运营管理系）
BODAME: Bilevel Optimization for Defense Against Model Extraction
Graduate School of Information Science and Technology, The University of Tokyo（东京大学信息科学与技术研究生院）；Center for Advanced Intelligence Project, RIKEN（理化学研究所先进智能项目中心）；Japan Science and Technology Agency（日本科学技术振兴机构）
Connecting Surrogate Safety Measures to Crash Probablity via Causal Probabilistic Time Series Prediction
University of California, Berkeley（加州大学伯克利分校）；Safe Transportation Research and Education Center（安全交通研究与教育中心）；Institute of Transportation Studies（交通研究所）
Normalized Conditional Mutual Information Surrogate Loss for Deep Neural Classifiers
Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, Canada（滑铁卢大学电气与计算机工程系）；The Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada（多伦多大学Edward S. Rogers Sr.电气与计算机工程系）
SURGIN: SURrogate-guided Generative INversion for subsurface multiphase flow with quantified uncertainty
Department of Geotechnical Engineering, College of Civil Engineering, Tongji University（同济大学土木工程学院地质工程系）；Key Laboratory of Geotechnical and Underground Engineering of Ministry of Education, Tongji University（教育部同济大学地质与地下工程重点实验室）；Physical Science and Engineering Division, King Abdullah University of Science and Technology (KAUST)（卡布斯科学与技术大学（KAUST）物理科学与工程系）；State Key Laboratory of Marine Geology, Tongji University（同济大学海洋地质国家重点实验室）；Tencent SSV（腾讯SSV）；Tencent SD（腾讯SD）
Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
State Key Laboratory of Blockchain and Data Security（区块链与数据安全国家重点实验室）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江）区块链与数据安全研究院）；Nanyang Technological University（南洋理工大学）
Sparse stochastic digital twins can outperform exact ones
Department of Computing and Mathematical Sciences, California Institute of Technology（计算与数学科学系，加州理工学院）；Department of Statistical Sciences, University of Toronto（统计科学系，多伦多大学）
