Rényi Differential Privacy

Follow this topic Ask about this topic

Latest papers

9 papers3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

TADP: Dual-Branch Temporally Adaptive Differential Privacy for Expression-Aware Video Anonymization
Oct 30, 2026Feng Xu, Xun Li, Lars Petersson +3Rényi Differential Privacy Differential Privacy
UNSW Sydney · CSIRO, Australia
Task-aware Kernel Stein certificates for Rényi differential privacy
Oct 16, 2026Leoni Carla Wirth, Tara Trauthwein, Gesine ReinertRényi Differential Privacy Differential Privacy
Department of Mathematics, Imperial College London, London SW7 2AZ, UK · Institute for Mathematical Stochastics, University of Münster, Münster, Germany · Department of Statistics, University of Oxford, Oxford OX1 3LB, UK
On Inherent Privacy of Posterior Sampling: A Unified Rényi-Divergence Framework
Oct 14, 2026Ruyu Zhou, Fang LiuRényi Differential Privacy Posterior Sampling
Department of Computer Science and Statistics University of Rhode Island · Department of ACMS University of Notre Dame
Can Rényi Accountants Beat Lossless Accountants for DP-SGD?
Oct 12, 2026Jinho BokPrivacy Accounting Rényi Differential Privacy
Department of Statistics and Data Science, University of Pennsylvania.
End-to-End Differential Privacy in Training Deep Neural Network Classifiers
Jul 21, 2026Huaiyuan Rao, Calvin Hawkins, Alexander Benvenuti +1Privacy-Preserving ML Differential Privacy
School of Electrical and Computer Engineering, Georgia Institute of Technology Atlanta, GA 30332, USA · School of Electrical and Computer Engineering, Georgia Institute of TechnologyJul Atlanta, GA 30332, USA
Differential Privacy of Gaussian Process Posterior Sampling
Jun 16, 2026Tomasz MaciazekGaussian Processes Privacy-Preserving ML
School of Mathematics, University of Bristol
Optimal Guarantees for Auditing Rényi Differentially Private Machine Learning
May 21, 2026Benjamin D. Kim, Lav R. Varshney, Daniel AlabiPrivacy Auditing Black-Box Model Auditing
University of Illinois Urbana-Champaign · 1Massachusetts Institute of Technology · Brook University
Differentially Private Model Merging
Apr 22, 2026Qichuan Yin, Manzil Zaheer, Tian LiPrivacy-Preserving ML Differential Privacy
The University of Chicago · Google DeepMind
Nonparametric Variational Differential Privacy via Embedding Parameter Clipping
Mar 10, 2026Dina El Zein, Shashi Kumar, James HendersonRényi Differential Privacy Privacy-Preserving Language Models
Idiap Research Institute, Switzerland · EPFL, Switzerland

Oct 30, 2026J/K move · Enter open · S save

TADP: Dual-Branch Temporally Adaptive Differential Privacy for Expression-Aware Video Anonymization

Feng Xu, Xun Li, Lars Petersson, Yulei Sui+2

UNSW Sydney · CSIRO, Australia

Rényi Differential Privacy Differential Privacy

Open paper AskPDF arXiv

We present TADP, a temporally adaptive differential privacy (DP) framework for inference-time privacy-preserving video generation under fixed-length clip-replacement adjacency. TADP uses a dual-branch design to extract identity and expression representations, clips and privatizes both branches with temporally adaptive Gaussian mechanisms whose noise scales depend only on preceding privatized releases within the same clip and are bounded below by history-uniform calibrated minima, and accounts for their joint release via adaptive Rényi Differential Privacy (RDP) composition. The clip-level RDP guarantee is converted to

(\varepsilon,δ)

-differential privacy, while soft quantization and subsequent temporal processing are applied only after privatization as DP post-processing. Experiments on facial expression datasets show reduced identity leakage under evaluated attacks, usable perceptual quality and temporal stability, and high facial expression recognition utility relative to the evaluated privacy-preserving baselines. TADP formally satisfies clip-level DP and empirically provides a favorable privacy--utility trade-off under the evaluated threat models and datasets.