Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning

11 January 2021

Papers citing "Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning"

50 / 151 papers shown

Title
Bounded and Unbiased Composite Differential Privacy Kai Zhang Yanjun Zhang Ruoxi Sun Pei-Wei Tsai M. Hassan Xingliang Yuan Minhui Xue Jinjun Chen 36 30 0 04 Nov 2023
Detecting Pretraining Data from Large Language Models Weijia Shi Anirudh Ajith Mengzhou Xia Yangsibo Huang Daogao Liu Terra Blevins Danqi Chen Luke Zettlemoyer MIALM 23 161 0 25 Oct 2023
A Cautionary Tale: On the Role of Reference Data in Empirical Privacy Defenses Caelin Kaplan Chuan Xu Othmane Marfoq Giovanni Neglia Anderson Santana de Oliveira AAML 44 1 0 18 Oct 2023
Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study Myeongseob Ko Ming Jin Chenguang Wang Ruoxi Jia 33 27 0 29 Sep 2023
Leave-one-out Distinguishability in Machine Learning Jiayuan Ye Anastasia Borovykh Soufiane Hayou Reza Shokri 31 9 0 29 Sep 2023
Differentially Private Computation of Basic Reproduction Numbers in Networked Epidemic Models Stefan Denner B. She C. Hawkins Alexander Benvenuti Brandon Fallin Philip E. Paré Matthew T. Hale 64 2 0 29 Sep 2023
Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey Lea Demelius Roman Kern Andreas Trügler SyDa FedML 30 6 0 28 Sep 2023
Privacy Side Channels in Machine Learning Systems Edoardo Debenedetti Giorgio Severi Nicholas Carlini Christopher A. Choquette-Choo Matthew Jagielski Milad Nasr Eric Wallace Florian Tramèr MIALM 32 38 0 11 Sep 2023
Revealing the True Cost of Locally Differentially Private Protocols: An Auditing Perspective Héber H. Arcolezi Sébastien Gambs 30 1 0 04 Sep 2023
Unlocking Accuracy and Fairness in Differentially Private Image Classification Leonard Berrada Soham De J. Shen Jamie Hayes Robert Stanforth David Stutz Pushmeet Kohli Samuel L. Smith Borja Balle 19 13 0 21 Aug 2023
Epsilon*: Privacy Metric for Machine Learning Models Diana M. Negoescu H. González Saad Eddin Al Orjany Jilei Yang Yuliia Lut ... Xinyi Zheng Zachariah Douglas Vidita Nolkha P. Ahammad G. Samorodnitsky 20 2 0 21 Jul 2023
Differentially Private Statistical Inference through $β$ -Divergence One Posterior Sampling Jack Jewson Sahra Ghalebikesabi Chris Holmes 25 2 0 11 Jul 2023
DP-Auditorium: a Large Scale Library for Auditing Differential Privacy William Kong Andrés Munoz Medina Mónica Ribero Umar Syed 16 2 0 10 Jul 2023
SoK: Privacy-Preserving Data Synthesis Yuzheng Hu Fan Wu Q. Li Yunhui Long Gonzalo Munilla Garrido Chang Ge Bolin Ding David A. Forsyth Bo-wen Li D. Song 52 25 0 05 Jul 2023
When Synthetic Data Met Regulation Georgi Ganev 19 2 0 01 Jul 2023
Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD Anvith Thudi Hengrui Jia Casey Meehan Ilia Shumailov Nicolas Papernot 17 3 0 01 Jul 2023
Gaussian Membership Inference Privacy Tobias Leemann Martin Pawelczyk Gjergji Kasneci 20 15 0 12 Jun 2023
AnoFel: Supporting Anonymity for Privacy-Preserving Federated Learning Ghada Almashaqbeh Zahra Ghodsi FedML 24 1 0 12 Jun 2023
Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting Ana-Maria Cretu Daniel Jones Yves-Alexandre de Montjoye Shruti Tople AAML 11 4 0 08 Jun 2023
PILLAR: How to make semi-private learning more effective Francesco Pinto Yaxian Hu Fanny Yang Amartya Sanyal 38 11 0 06 Jun 2023
Unleashing the Power of Randomization in Auditing Differentially Private ML Krishna Pillutla Galen Andrew Peter Kairouz H. B. McMahan Alina Oprea Sewoong Oh 25 20 0 29 May 2023
Training Data Extraction From Pre-trained Language Models: A Survey Shotaro Ishihara 24 46 0 25 May 2023
Privacy Auditing with One (1) Training Run Thomas Steinke Milad Nasr Matthew Jagielski 25 76 0 15 May 2023
ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees Sina Sajadmanesh D. Gática-Pérez 17 15 0 18 Apr 2023
A Randomized Approach for Tight Privacy Accounting Jiachen T. Wang Saeed Mahloujifar Tong Wu R. Jia Prateek Mittal 28 9 0 17 Apr 2023
Exploring the Benefits of Visual Prompting in Differential Privacy Yizhe Li Yu-Lin Tsai Xuebin Ren Chia-Mu Yu Pin-Yu Chen AAML VPVLM 11 18 0 22 Mar 2023
Can Membership Inferencing be Refuted? Zhifeng Kong A. Chowdhury Kamalika Chaudhuri MIALM MIACV 19 6 0 07 Mar 2023
How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy Natalia Ponomareva Hussein Hazimeh Alexey Kurakin Zheng Xu Carson E. Denison H. B. McMahan Sergei Vassilvitskii Steve Chien Abhradeep Thakurta 94 167 0 01 Mar 2023
Tight Auditing of Differentially Private Machine Learning Milad Nasr Jamie Hayes Thomas Steinke Borja Balle Florian Tramèr Matthew Jagielski Nicholas Carlini Andreas Terzis FedML 25 52 0 15 Feb 2023
Bounding Training Data Reconstruction in DP-SGD Jamie Hayes Saeed Mahloujifar Borja Balle AAML FedML 26 39 0 14 Feb 2023
One-shot Empirical Privacy Estimation for Federated Learning Galen Andrew Peter Kairouz Sewoong Oh Alina Oprea H. B. McMahan Vinith M. Suriyakumar FedML 19 32 0 06 Feb 2023
"Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice Giovanni Apruzzese Hyrum S. Anderson Savino Dambra D. Freeman Fabio Pierazzi Kevin A. Roundy AAML 27 75 0 29 Dec 2022
SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning A. Salem Giovanni Cherubin David E. Evans Boris Köpf Andrew J. Paverd Anshuman Suri Shruti Tople Santiago Zanella Béguelin 31 35 0 21 Dec 2022
Differentially Private Image Classification from Features Harsh Mehta Walid Krichene Abhradeep Thakurta Alexey Kurakin Ashok Cutkosky 43 7 0 24 Nov 2022
Private Multi-Winner Voting for Machine Learning Adam Dziedzic Christopher A. Choquette-Choo Natalie Dullerud Vinith M. Suriyakumar Ali Shahin Shamsabadi Muhammad Ahmad Kaleem S. Jha Nicolas Papernot Xiao Wang 27 1 0 23 Nov 2022
Privacy in Practice: Private COVID-19 Detection in X-Ray Images (Extended Version) Lucas Lange Maja Schneider Peter Christen Erhard Rahm 16 7 0 21 Nov 2022
A Unified Framework for Quantifying Privacy Risk in Synthetic Data M. Giomi Franziska Boenisch C. Wehmeyer Borbála Tasnádi 11 56 0 18 Nov 2022
Provable Membership Inference Privacy Zachary Izzo Jinsung Yoon Sercan Ö. Arik James Y. Zou 31 5 0 12 Nov 2022
TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data F. Houssiau James Jordon Samuel N. Cohen Owen Daniel Andrew Elliott James Geddes C. Mole Camila Rangel Smith Lukasz Szpruch 15 45 0 12 Nov 2022
Amplifying Membership Exposure via Data Poisoning Yufei Chen Chao Shen Yun Shen Cong Wang Yang Zhang AAML 43 27 0 01 Nov 2022
Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano Chuan Guo Alexandre Sablayrolles Maziar Sanjabi FedML 21 17 0 24 Oct 2022
Generalised Likelihood Ratio Testing Adversaries through the Differential Privacy Lens Georgios Kaissis Alexander Ziller Stefan Kolek Martinez de Azagra Daniel Rueckert 7 0 0 24 Oct 2022
A General Framework for Auditing Differentially Private Machine Learning Fred Lu Joseph Munoz Maya Fuchs Tyler LeBlond Elliott Zaresky-Williams Edward Raff Francis Ferraro Brian Testa FedML 11 35 0 16 Oct 2022
Differentially Private Deep Learning with ModelMix Hanshen Xiao Jun Wan S. Devadas 8 3 0 07 Oct 2022
PAC Privacy: Automatic Privacy Measurement and Control of Data Processing Hanshen Xiao S. Devadas 13 11 0 07 Oct 2022
CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning Samuel Maddock Alexandre Sablayrolles Pierre Stock FedML 8 22 0 06 Oct 2022
No Free Lunch in "Privacy for Free: How does Dataset Condensation Help Privacy" Nicholas Carlini Vitaly Feldman Milad Nasr DD 40 17 0 29 Sep 2022
Algorithms that Approximate Data Removal: New Results and Limitations Vinith M. Suriyakumar Ashia C. Wilson MU 40 27 0 25 Sep 2022
M^4I: Multi-modal Models Membership Inference Pingyi Hu Zihan Wang Ruoxi Sun Hu Wang Minhui Xue 37 26 0 15 Sep 2022
SNAP: Efficient Extraction of Private Properties with Poisoning Harsh Chaudhari John Abascal Alina Oprea Matthew Jagielski Florian Tramèr Jonathan R. Ullman MIACV 26 30 0 25 Aug 2022