Computing Differential Privacy Guarantees for Heterogeneous Compositions
Using FFT

v1v2 (latest)

Computing Differential Privacy Guarantees for Heterogeneous Compositions Using FFT

24 February 2021

ArXiv (abs)PDF HTML

Papers citing "Computing Differential Privacy Guarantees for Heterogeneous Compositions Using FFT"

17 / 17 papers shown

Title
PREAMBLE: Private and Efficient Aggregation of Block Sparse Vectors and Applications Hilal Asi Vitaly Feldman Hannah Keller G. Rothblum Kunal Talwar FedML 117 1 0 14 Mar 2025
$(\varepsilon, δ)$ Considered Harmful: Best Practices for Reporting Differential Privacy Guarantees Juan Felipe Gomez B. Kulynych G. Kaissis Jamie Hayes Borja Balle Antti Honkela 104 0 0 13 Mar 2025
Weights Shuffling for Improving DPSGD in Transformer-based Models Jungang Yang Zhe Ji Liyao Xiang 101 0 0 22 Jul 2024
Closed-Form Bounds for DP-SGD against Record-level Inference Giovanni Cherubin Boris Köpf Andrew Paverd Shruti Tople Lukas Wutschitz Santiago Zanella Béguelin 89 2 0 22 Feb 2024
Private Fine-tuning of Large Language Models with Zeroth-order Optimization Xinyu Tang Ashwinee Panda Milad Nasr Saeed Mahloujifar Prateek Mittal 218 26 0 09 Jan 2024
Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation Jiachen T. Wang Yuqing Zhu Yu Wang R. Jia Prateek Mittal TDI 107 12 0 30 Aug 2023
Privacy-Preserving In-Context Learning for Large Language Models Tong Wu Ashwinee Panda Jiachen T. Wang Prateek Mittal 114 32 0 02 May 2023
A Randomized Approach for Tight Privacy Accounting Jiachen T. Wang Saeed Mahloujifar Tong Wu R. Jia Prateek Mittal 106 10 0 17 Apr 2023
Composition of Differential Privacy & Privacy Amplification by Subsampling Thomas Steinke 136 54 0 02 Oct 2022
Individual Privacy Accounting with Gaussian Differential Privacy A. Koskela Marlon Tobaben Antti Honkela 107 20 0 30 Sep 2022
The Saddle-Point Accountant for Differential Privacy Wael Alghamdi S. Asoodeh Flavio du Pin Calmon Juan Felipe Gomez O. Kosut Lalitha Sankar Fei Wei 65 7 0 20 Aug 2022
Faster Privacy Accounting via Evolving Discretization Badih Ghazi Pritish Kamath Ravi Kumar Pasin Manurangsi 104 14 0 10 Jul 2022
Connect the Dots: Tighter Discrete Approximations of Privacy Loss Distributions Vadym Doroshenko Badih Ghazi Pritish Kamath Ravi Kumar Pasin Manurangsi 79 43 0 10 Jul 2022
Learning Numeric Optimal Differentially Private Truncated Additive Mechanisms David M. Sommer Lukas Abfalterer Sheila Zingg Esfandiar Mohammadi 29 4 0 27 Jul 2021
Optimal Accounting of Differential Privacy via Characteristic Function Yuqing Zhu Jinshuo Dong Yu Wang 64 104 0 16 Jun 2021
Numerical Composition of Differential Privacy Sivakanth Gopi Y. Lee Lukas Wutschitz 92 183 0 05 Jun 2021
Tight Accounting in the Shuffle Model of Differential Privacy A. Koskela Mikko A. Heikkilä Antti Honkela FedML 65 17 0 01 Jun 2021