Privacy Preserving Machine Learning

Virtual ACM CCS 2021 Workshop
November 19, 2021


This one day workshop focuses on privacy preserving techniques for training, inference, and disclosure in large scale data analysis, both in the distributed and centralized settings. We have observed increasing interest of the Machine Learning (ML) community in leveraging cryptographic techniques such as Multi-Party Computation (MPC) and Homomorphic Encryption (HE) for privacy preserving training and inference, as well as Differential Privacy (DP) for disclosure. Simultaneously, the systems security and cryptography community has proposed various secure frameworks for ML. We encourage both theory and application-oriented submissions exploring a range of approaches, including

  • Differential privacy and other statistical notions of privacy: theory, applications, and implementations
  • Secure multi-party computation techniques for ML
  • Learning on encrypted data
  • Hardware-based approaches to privacy-preserving ML
  • Trade-offs between privacy and utility
  • Privacy attacks
  • Federated and decentralized privacy-preserving algorithms
  • Programming languages for privacy-preserving data analysis
  • Policy-making aspects of data privacy
  • Interplay between privacy and adversarial robustness in machine learning
  • Relations between privacy, fairness and transparency
  • Applications of privacy-preserving ML

Call For Papers & Important Dates

Download Full CFP

Submission deadline: July 22 August 1, 2021, 23:59 (Anywhere on Earth)
Notification of acceptance: September 16, 2021
Workshop: November 19, 2021

Submission Instructions

Submissions in the form of extended abstracts must be at most 4 pages long (not including references), using the double-column ACM format. We encourage submission of work that is new to the privacy-preserving machine learning community. Submissions should be anonymized. The workshop will not have formal proceedings, but authors of accepted abstracts can choose to have a link to a preprint or a PDF published on the workshop webpage. Authors of accepted papers are required to register for the workshop but can present their work remotely.

Submit Your Abstract

Invited Speakers


Workshop organizers

  • James Bell (The Alan Turing Institute)
  • Aurélien Bellet (INRIA)
  • Adrià Gascón (Google)
  • Olya Ohrimenko (The University of Melbourne)
  • Mariana Raykova (Google)
  • Phillipp Schoppmann (Google)
  • Carmela Troncoso (EPFL)

Program Committee

  • Carsten Baum (Aarhus University)
  • Hao Chen (Facebook)
  • Giovanni Cherubin (The Alan Turing Institute)
  • Albert Cheu (Northeastern)
  • Graham Cormode (University of Warwick)
  • Morten Dahl (Cape Privacy)
  • Daniel Demmler (Hamburg University)
  • Antti Honkela (University of Helsinki)
  • Bargav Jayaraman (University of Virginia)
  • Dali Kaafar (Macquarie University)
  • Peter Kairouz (Google)
  • Marcel Keller (CSIRO's Data61)
  • Ágnes Kiss (CISPA Helmholtz Center)
  • Antti Koskela (University of Helsinki)
  • Kim Laine (Microsoft Research)
  • Eleftheria Makri (KU Leuven)
  • Peihan Miao (University of Illinois at Chicago)
  • Catuscia Palamidessi (Ecole Polytechnique & Inria)
  • Rachel Player (Royal Holloway)
  • Ananth Ragunathan (Facebook)
  • Divya Ravi (Aarhus University)
  • Leonie Reichert (HU Berlin)
  • Peter Rindal (Visa Research)
  • Dragos Rotaru (Cape Privacy)
  • Prateek Saxena (National University of Singapore)
  • Peter Scholl (Aarhus University)
  • Reza Shokri (National University of Singapore)
  • Mark Simkin (Aarhus University)
  • Nigel Smart (KU Leuven)
  • Oleksandr Tkachenko (TU Darmstadt)
  • Juan Ramón Troncoso-Pastoriza (EPFL)
  • Jon Ullman (Northeastern)
  • Jalaj Upadhyay (Apple)
  • Sameer Wagh (Berkeley)
  • Xiao Wang (Northwestern University)
  • Christian Weinert (TU Darmstadt)
  • Sophia Yakoubov (Aarhus University)
  • Yang Zhang (CISPA Helmholtz Center)

Previous Editions