Alexandre Sablayrolles

Researcher, Facebook

Joined

November 2017

Names

Alexandre Sablayrolles

Emails

****@gmail.com (Confirmed)

,

****@fb.com (Confirmed)

Personal Links

Career & Education History

Researcher

Facebook (fb.com)

2020 – Present

PhD student

Facebook (fb.com)

2017 – 2020

Advisors, Relations & Conflicts

PhD Advisor

Cordelia Schmid

2017 – 2020

PhD Advisor

2017 – 2020

PhD Advisor

2017 – 2020

Expertise

privacy

2018 – Present

approximate nearest neighbor search

2017 – Present

deep learning

2017 – Present

Publications

TAN Without a Burn: Scaling Laws of DP-SGD
Tom Sander, Pierre Stock, Alexandre Sablayrolles
- ICML 2023 Poster
- Readers: Everyone
Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano
Chuan Guo, Alexandre Sablayrolles, Maziar Sanjabi
- ICML 2023 Poster
- Readers: Everyone
Optimal Membership Inference Bounds for Adaptive Composition of Sampled Gaussian Mechanisms
Saeed Mahloujifar, Alexandre Sablayrolles, Graham Cormode, Somesh Jha
- Published: 01 Feb 2023, Last Modified: 13 Feb 2023
- Submitted to ICLR 2023
- Readers: Everyone
CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning
Samuel Maddock, Alexandre Sablayrolles, Pierre Stock
- Published: 01 Feb 2023, Last Modified: 14 Jan 2026
- ICLR 2023 poster
- Readers: Everyone
Defending against Reconstruction attacks using Rényi Differential Privacy
Pierre Stock, Igor Shilov, Ilya Mironov, Alexandre Sablayrolles
- Published: 01 Feb 2023, Last Modified: 14 Jan 2026
- Submitted to ICLR 2023
- Readers: Everyone
TAN without a burn: Scaling laws of DP-SGD
Tom Sander, Pierre Stock, Alexandre Sablayrolles
- Published: 01 Feb 2023, Last Modified: 14 Jan 2026
- Submitted to ICLR 2023
- Readers: Everyone
Defending against Reconstruction Attacks with Rényi Differential Privacy
Pierre Stock, Igor Shilov, Ilya Mironov, Alexandre Sablayrolles
- 2022 (modified: 02 Mar 2022)
- CoRR 2022
- Readers: Everyone
On the Importance of Difficulty Calibration in Membership Inference Attacks
Lauren Watson, Chuan Guo, Graham Cormode, Alexandre Sablayrolles
- Published: 28 Jan 2022, Last Modified: 12 Oct 2025
- ICLR 2022 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: 30 Dec 2025
- PRIML 2021 Poster
- Readers: Everyone
Going deeper with Image Transformers
Hugo Touvron, Matthieu Cord, Alexandre Sablayrolles, Gabriel Synnaeve, Hervé Jégou
- 2021 (modified: 21 Feb 2024)
- CoRR 2021
- Readers: Everyone

View all 33 publications

Co-Authors

View all 36 co-authors