10 papers
CALLIOPE: Private Insights into AI Use, Without Embeddings
Edith Cohen, Vadym Doroshenko, Badih Ghazi +11
We introduce CALLIOPE, a top-down framework for discovering topic hierarchies in large corpora of unstructured data (e.g., LLM conversations), while supporting differential privacy…
Tight Lower Bounds for Differentially Private Continual Counting
Charlie Harrison, Ethan Leeman
The Binary Tree Mechanism is a standard algorithm for differentially private continual counting, but its asymptotic optimality under pure differential privacy has remained unresolv…
Traceable Trust for action-ready artificial intelligence in bioscience
Huayu Xin, Yizhi Cai, Mukilan Deivarajan Suresh +9
Artificial intelligence (AI) is becoming part of the working infrastructure of the biosciences. AI models can predict biomolecular structures, design proteins, rank variants, annot…
Optimal partition selection with Rényi differential privacy
Charlie Harrison, Pasin Manurangsi
A common problem in private data analysis is the partition selection problem, where each user holds a set of partitions (e.g. keys in a GROUP BY operation) from a possibly unbounde…
Exact zCDP Characterizations for Fundamental Differentially Private Mechanisms
Charlie Harrison, Pasin Manurangsi
Zero-concentrated differential privacy (zCDP) is a variant of differential privacy (DP) that is widely used partly thanks to its nice composition property. While a tight conversion…
Infinitely Divisible Noise for Differential Privacy: Nearly Optimal Error in the High Regime
Charlie Harrison, Pasin Manurangsi
Differential privacy (DP) can be achieved in a distributed manner, where multiple parties add independent noise such that their sum protects the overall dataset with DP. A common t…
On the Differential Privacy and Interactivity of Privacy Sandbox Reports
Badih Ghazi, Charlie Harrison, Arpana Hosabettu +8
The Privacy Sandbox initiative from Google includes APIs for enabling privacy-preserving advertising functionalities as part of the effort around limiting third-party cookies. In p…
Balls-and-Bins Sampling for DP-SGD
Lynn Chua, Badih Ghazi, Charlie Harrison +6
We introduce the Balls-and-Bins sampling for differentially private (DP) optimization methods such as DP-SGD. While it has been common practice to use some form of shuffling in DP-…
Differentially Private Ad Conversion Measurement
John Delaney, Badih Ghazi, Charlie Harrison +6
In this work, we study ad conversion measurement, a central functionality in digital advertising, where an advertiser seeks to estimate advertiser website (or mobile app) conversio…
Training Differentially Private Ad Prediction Models with Semi-Sensitive Features
Lynn Chua, Qiliang Cui, Badih Ghazi +9
Motivated by problems arising in digital advertising, we introduce the task of training differentially private (DP) machine learning models with semi-sensitive features. In this se…