We show that differentially private stochastic gradient descent (DP-SGD) can yield poorly calibrated, overconfident deep learning models. This represents a serious issue for safety-critical applications, e.g. in medical diagnosis. We highlight and exploit parallels between stochastic gradient Langevin dynamics, a scalable Bayesian inference technique for training deep neural networks, and DP-SGD, in order to train differentially private, Bayesian neural networks with minor adjustments to the original (DP-SGD) algorithm. Our approach provides considerably more reliable uncertainty estimates than DP-SGD, as demonstrated empirically by a reduction in expected calibration error (MNIST $\sim{5}$-fold, Pediatric Pneumonia Dataset $\sim{2}$-fold).
Tighter Generalization Bounds for Iterative Differentially Private Learning Algorithms
UBTECH Sydney AI Centre, School of Computer Science, Faculty of Engineering, the University of Sydney（悉尼大学工程学院计算机科学学院优必选悉尼人工智能中心）；University of Science and Technology of China（中国科学技术大学）
Communication-Efficient and Differentially Private Vertical Federated Learning with Zeroth-Order Optimization
Elmore Family School of Electrical and Computer Engineering, Purdue University（电气与计算机工程学院，普渡大学）；Department of Computer Science and Engineering, Yonsei University（计算机科学与工程系，延世大学）
ScoreShield: Differentially Private Release of Similarity Scores
School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院）；School of Engineering, École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院工程学院）
Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise
School of Data and Sciences（数据与科学学院）；BRAC University（布拉克大学）；Electrical and Computer Engineering（电气与计算机工程）；University of California, Santa Barbara（加州大学圣巴巴拉分校）；Electrical and Electronic Engineering（电气与电子工程）；Bangladesh University Engineering and Technology（孟加拉工程与技术大学）
$(ε, δ)$-Differentially Private Partial Least Squares Regression
Software Competence Center Hagenberg (SCCH) GmbH（哈根伯格软件能力中心有限公司）；Faculty of Computer Science and Electrical Engineering（计算机科学与电气工程学院）；University of Rostock（罗斯托克大学）
Calibrated Adaptation: Bayesian Stiefel Manifold Priors for Reliable Parameter-Efficient Fine-Tuning
Department of Computer Science, Iowa State University（计算机科学系，爱荷华州立大学）；Department of Civil, Construction and Environmental Engineering, Iowa State University（土木、建设与环境工程系，爱荷华州立大学）
SMA-DP: Spectral Memory-Aware Differential Privacy for Deep Learning
Department of Electrical Engineering and Computer Science（电气工程与计算机科学系）；University of California, Merced（加州大学默塞德分校）；Department of Applied Mathematics（应用数学系）
Content-Aware Differential Privacy with Conditional Invertible Neural Networks
Heidelberg University Hospital（海德堡大学医院）；Ruprecht-Karls University Heidelberg（海德堡鲁普雷希特-卡尔斯大学）；DZHK (German Centre for Cardiovascular Research)（德国心血管研究中心）
Stabilization of Perturbed Loss Function: Differential Privacy without Gradient Noise
Department of Computer Science and Engineering, University of Texas at Arlington（计算机科学与工程系，德克萨斯大学阿灵顿分校）；School of Electrical, Computer and Energy Engineering, Arizona State University（电气、计算机与能源工程学院，亚利桑那州立大学）
Validated Synthetic Patient Generation for Small Longitudinal Cohorts: Coagulation Dynamics Across Pregnancy
Robert F. Smith School of Chemical and Biomolecular Engineering, Cornell University（康奈尔大学罗伯特·F·史密斯化学与生物分子工程学院）；Department of Biochemistry, The Robert Larner, M.D. College of Medicine, University of Vermont Medical Center（佛蒙特大学医学中心罗伯特·拉纳医学院生物化学系）；Department of Obstetrics, Gynecology, and Reproductive Sciences, The Robert Larner, M.D. College of Medicine, University of Vermont Medical Center（佛蒙特大学医学中心罗伯特·拉纳医学院妇产科与生殖科学系）
DECODE: Dual-Enhanced Conditioned Diffusion for EEG Forecasting
Concordia Institute for Information Systems Engineering (CIISE), Concordia University, Canada. Department of Electrical；Computer Engineering, University of Toronto, Canada
