Cover Image

Differentially Private Synthetic Data Release for Topics API Outputs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dick, Travis, Epasto, Alessandro, Javanmard, Adel, Karlin, Josh, Medina, Andres Munoz, Mirrokni, Vahab, Vassilvitskii, Sergei, Zhong, Peilin
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank
by: Epasto, Alessandro, et al.
Published: (2022)

Improving the Variance of Differentially Private Randomized Experiments through Clustering
by: Javanmard, Adel, et al.
Published: (2023)

Perturb-and-Project: Differentially Private Similarities and Marginals
by: Cohen-Addad, Vincent, et al.
Published: (2024)

Retraining with Predicted Hard Labels Provably Increases Model Accuracy
by: Das, Rudrajit, et al.
Published: (2024)

Smooth Anonymity for Sparse Graphs
by: Epasto, Alessandro, et al.
Published: (2022)

Differentially Private Clustering in Data Streams
by: Epasto, Alessandro, et al.
Published: (2023)

Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing
by: Javanmard, Adel, et al.
Published: (2025)

Private Training & Data Generation by Clustering Embeddings
by: Zhou, Felix, et al.
Published: (2025)

Differentially Private Space-Efficient Algorithms for Counting Distinct Elements in the Turnstile Model
by: Cummings, Rachel, et al.
Published: (2025)

Practical Considerations for Differential Privacy
by: Amin, Kareem, et al.
Published: (2024)

Understanding the Role of Training Data in Test-Time Scaling
by: Javanmard, Adel, et al.
Published: (2025)

Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models
by: Javanmard, Adel, et al.
Published: (2026)

PriorBoost: An Adaptive Algorithm for Learning from Aggregate Responses
by: Javanmard, Adel, et al.
Published: (2024)

DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
by: Zhang, Xinwei, et al.
Published: (2024)

Missing Mass for Differentially Private Domain Discovery
by: Dick, Travis, et al.
Published: (2026)

Learning Rate Schedules in the Presence of Distribution Shift
by: Fahrbach, Matthew, et al.
Published: (2023)

Optimistic Rates for Learning from Label Proportions
by: Li, Gene, et al.
Published: (2024)

Keeping a Secret Requires a Good Memory: Space Lower-Bounds for Private Algorithms
by: Epasto, Alessandro, et al.
Published: (2026)

Differentially Private Optimization for Non-Decomposable Objective Functions
by: Kong, Weiwei, et al.
Published: (2023)

Sublinear Space Graph Algorithms in the Continual Release Model
by: Epasto, Alessandro, et al.
Published: (2024)

Optimal Approximation -- Smoothness Tradeoffs for Soft-Max Functions
by: Epasto, Alessandro, et al.
Published: (2020)

Scalable Private Partition Selection via Adaptive Weighting
by: Chen, Justin Y., et al.
Published: (2025)

Titans: Learning to Memorize at Test Time
by: Behrouz, Ali, et al.
Published: (2024)

PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels
by: Kacham, Praneeth, et al.
Published: (2023)

Is API Access to LLMs Useful for Generating Private Synthetic Tabular Data?
by: Swanberg, Marika, et al.
Published: (2025)

Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
by: Javanmard, Adel, et al.
Published: (2024)

The Privacy-Utility Trade-off in the Topics API
by: Alvim, Mário S., et al.
Published: (2024)

Private prediction for large-scale synthetic text generation
by: Amin, Kareem, et al.
Published: (2024)

Aim High, Stay Private: Differentially Private Synthetic Data Enables Public Release of Behavioral Health Information with High Utility
by: Ghasemizade, Mohsen, et al.
Published: (2025)

Continual Release of Differentially Private Synthetic Data from Longitudinal Data Collections
by: Bun, Mark, et al.
Published: (2023)

Differentially Private Release and Learning of Threshold Functions
by: Bun, Mark, et al.
Published: (2015)

Maximum Coverage in Turnstile Streams with Applications to Fingerprinting Measures
by: Ene, Alina, et al.
Published: (2025)

A Public and Reproducible Assessment of the Topics API on Real Data
by: Beugin, Yohan, et al.
Published: (2024)

Differentially Private Model-X Knockoffs via Johnson-Lindenstrauss Transform
by: Tao, Yuxuan, et al.
Published: (2025)

Benchmarking Private Population Data Release Mechanisms: Synthetic Data vs. TopDown
by: Maddi, Aadyaa, et al.
Published: (2024)

Differentially Private Continual Release of Histograms and Related Queries
by: Henzinger, Monika, et al.
Published: (2023)

A Quantitative Information Flow Analysis of the Topics API
by: Alvim, Mário S., et al.
Published: (2023)

Subset-Based Instance Optimality in Private Estimation
by: Dick, Travis, et al.
Published: (2023)

Releasing Differentially Private Event Logs Using Generative Models
by: Wangelik, Frederik, et al.
Published: (2025)

Output Perturbation for Differentially Private Convex Optimization: Faster and More General
by: Lowy, Andrew, et al.
Published: (2021)