NeurIPS 2021 Workshop PRIML Submissions

Communication Efficient Federated Learning with Secure Aggregation and Differential Privacy
Wei-Ning Chen, Christopher A. Choquette-Choo, Peter Kairouz
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
Realistic Face Reconstruction from Deep Embeddings
Edward Vendrow, Joshua Vendrow
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
Mean Estimation with User-level Privacy under Data Heterogeneity
Rachel Cummings, Vitaly Feldman, Audra McMillan, Kunal Talwar
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
Label Private Deep Learning Training based on Secure Multiparty Computation and Differential Privacy
Sen Yuan, Milan Shen, Ilya Mironov, Anderson Nascimento
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
DP-SEP: Differentially private stochastic expectation propagation
Margarita Vinaroz, Mijung Park, Mijung Park
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
Private Confidence Sets
Karan Chadha, John Duchi, Rohith Kuditipudi
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
A Joint Exponential Mechanism for Differentially Private Top-k Set
Andres Munoz medina, Matthew Joseph, Jennifer Gillenwater, Mónica Ribero
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
Certified Predictions using MPC-Friendly Publicly Verifiable Covertly Secure Commitments
Nitin Agrawal, James Bell, Adrià Gascón, Matt Kusner
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
SoK: Privacy-preserving Clustering (Extended Abstract)
Aditya Hegde, Helen Möllering, Thomas Schneider, Hossein Yalame
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Oral
- Readers: Everyone
A Generic Hybrid 2PC Framework with Application to Private Inference of Unmodified Neural Networks (Extended Abstract)
Lennart Braun, Rosario Cammarota, Thomas Schneider
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
ABY2.0: New Efficient Primitives for STPC with Applications to Privacy in Machine Learning (Extended Abstract)
Arpita Patra, Thomas Schneider, Ajith Suresh, Hossein Yalame
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
Characterizing and Improving MPC-based Private Inference for Transformer-based Models
Yongqin Wang, Edward Suh, Wenjie Xiong, Brian Knott, Benjamin Lefaudeux, Murali Annavaram, Hsien-Hsin Lee
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
Combining Public and Private Data
Cecilia Ferrando, Jennifer Gillenwater, Alex Kulesza
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
Adversarial Detection Avoidance Attacks: Evaluating the robustness of perceptual hashing-based client-side scanning
Shubham Jain, Ana-Maria Cretu, Yves-Alexandre de Montjoye
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods
Terrance Liu, Giuseppe Vietri, Steven Wu
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
Unsupervised Membership Inference Attacks Against Machine Learning Models
Yuefeng Peng
- Published: 04 Nov 2021, Last Modified: 02 Nov 2023
- PRIML 2021 Poster
- Readers: Everyone
A Novel Self-Distillation Architecture to Defeat Membership Inference Attacks
Xinyu Tang, Saeed Mahloujifar, Liwei Song, Virat Shejwalkar, Milad Nasr, Amir Houmansadr, Prateek Mittal
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
Efficient passive membership inference attack in federated learning
Oualid Zari, Chuan Xu, Giovanni Neglia
- Published: 04 Nov 2021, Last Modified: 12 Mar 2024
- PRIML 2021 Poster
- Readers: Everyone
Enforcing fairness in private federated learning via the modified method of differential multipliers
Borja Rodríguez Gálvez, Filip Granqvist, Rogier van Dalen, Matt Seigel
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
Membership Inference Attacks Against NLP Classification Models
Virat Shejwalkar, Huseyin A Inan, Amir Houmansadr, Robert Sim
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Poster
- Readers: Everyone
An automatic differentiation system for the age of differential privacy
Dmitrii Usynin, Alexander Ziller, Moritz Knolle, Daniel Rueckert, Georgios Kaissis
- Published: 04 Nov 2021, Last Modified: 12 Mar 2024
- PRIML 2021 Poster
- Readers: Everyone
Opacus: User-Friendly Differential Privacy Library in PyTorch
Ashkan Yousefpour, Igor Shilov, Alexandre Sablayrolles, Davide Testuggine, Karthik Prasad, Mani Malek, John Nguyen, Sayan Ghosh, Akash Bharadwaj, Jessica Zhao, Graham Cormode, Ilya Mironov
- Published: 04 Nov 2021, Last Modified: 12 Mar 2024
- PRIML 2021 Poster
- Readers: Everyone
Simple Baselines Are Strong Performers for Differentially Private Natural Language Processing
Xuechen Li, Florian Tramer, Percy Liang, Tatsunori Hashimoto
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Oral
- Readers: Everyone
Differential Privacy via Group Shuffling
Amir Mohammad Abouei, Clement Louis Canonne
- Published: 04 Nov 2021, Last Modified: 15 May 2023
- PRIML 2021 Oral
- Readers: Everyone
Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Design
Felix Morsbach, Tobias Dehling, Ali Sunyaev
- Published: 04 Nov 2021, Last Modified: 12 Mar 2024
- PRIML 2021 Poster
- Readers: Everyone