Privacy in Machine Learning (PriML) at NeurIPS 2021 Workshop

Privacy in Machine Learning (PriML) at NeurIPS 2021 Workshop

Mon Nov-1-2021 | 12:00am - Mon Nov-1-2021 | 01:00am

Organizer: Borja Balle (DeepMind) Giovanni Cherubin (Alan Turing Institute) Kamalika Chaudhuri (UC San Diego and Facebook AI Research)

Description

Our one-day workshop at NeurIPS 2021 focuses on privacy-preserving machine learning techniques for large-scale data analysis, both in the distributed and centralized settings and on scenarios that highlight the importance and need for these techniques (e.g., via privacy attacks). There is growing interest from the Machine Learning (ML) community in leveraging cryptographic techniques such as Multi-Party Computation (MPC) and Homomorphic Encryption (HE) for secure computation during training and inference, as well as Differential Privacy (DP) for limiting the privacy risks from the trained model itself. We encourage both theory and application-oriented submissions exploring a range of approaches listed below. 

  • Privacy-preserving machine learning
  • Differential privacy: theory, applications, and implementations
  • Statistical and information-theoretic notions of privacy, including DP relaxations
  • Empirical and theoretical comparisons between different notions of privacy
  • Privacy-preserving data sharing, anonymization, and privacy of synthetic data
  • Privacy attacks
  • Federated and decentralized privacy-preserving algorithms
  • Policy-making aspects of data privacy
  • Secure multi-party computation techniques for machine learning
  • Learning on encrypted data, homomorphic encryption
  • Privacy in autonomous systems
  • Online social networks privacy
  • Privacy and private learning in computer vision and natural language processing tasks
  • Programming languages for privacy-preserving data analysis
  • Relations of privacy with fairness, transparency, and adversarial robustness
  • Machine unlearning and data-deletion

# Submission instructions

Submissions in the form of extended abstracts must be at most 4 pages long (not including references; additional supplementary material may be submitted but may be ignored by reviewers), non-anonymized, and adhere to the NeurIPS format. We encourage the submission of work that is new to the privacy-preserving machine learning community. Submissions solely based on work that has been previously published in conferences on machine learning and related fields are not suitable for the workshop. On the other hand, we allow submission of works currently under submission and relevant works recently previously published in privacy and security venues. Submission of work under review at NeurIPS 2021 is allowed but this must be disclosed at submission time. Submissions accepted to the NeurIPS main conference may be deprioritized in selecting oral presentations. The workshop will not have formal proceedings, but authors of accepted abstracts can choose to have a link to arxiv or a pdf added on the workshop webpage.

- Submission URL: https://openreview.net/group?id=NeurIPS.cc/2021/Workshop/PRIML

Submission deadline: September 16, 2021

- Notification of acceptance: October 15, 2021

- Video and slides submission deadline (for accepted papers): November 1, 2021

- Virtual workshop: Tuesday, December 14, 2021

- Website: https://priml2021.github.io/


# Organizers

  • Borja Balle (DeepMind)

  • Giovanni Cherubin (Alan Turing Institute)

  • Kamalika Chaudhuri (UC San Diego and Facebook AI Research)

  • Antti Honkela (University of Helsinki)

  • Jonathan Lebensold (Mila and McGill University)

  • Casey Meehan (UC San Diego)

  • Mijung Park (University of British Columbia)

  • Yu-Xiang Wang (UC Santa Barbara)

  • Adrian Weller (Alan Turing Institute & Cambridge University)

  • Yuqing Zhu (UC Santa Barbara)

 

 

Register

Conference link

Details

  • Date and Time

    Start: Mon Nov-1-2021 | 12:00am

    End: Mon Nov-1-2021 | 01:00am

  • Timezone

    (GMT-11:00) Midway Island

  • Location

    Online

  • Event Type

    Workshop

  • Verticals

    Machine Learning ,Multi-Party Computation,Homomorphic Encryption

  • Posted by
    Academic Gates
    Academic Gates

    November 01 2021

Share the event

Other events

HEAR 2021 NeurIPS Challenge (Holistic Evaluation of Audio Representations)
  • 01:00am Jul-5-2021
         11:30pm Oct-31-2021
  • Virtual
  • We invite you to participate in the HEAR 2021 NeurIPS Challenge (Holistic Evaluation of Audio Repres...
View more
Online

Jul-5-2021 | 01:00am

HEAR 2021 NeurIPS Challenge (Holistic Evaluat...

HEAR 2021 Committee

United States

The 10th International Conference on Complex Networks and their Applications
  • 12:00am - 01:00am | Oct-30-2021
  • Madrid
  • Authors are encouraged to submit both theoretical and applied papers on their research in ...
View more
Online

Oct-30-2021 | 12:00am

The 10th International Conference on Complex ...

Complex Networks

Sweden

8th International Conference on Information Management and Big Data
  • 12:00am Dec-1-2021
         01:00am Dec-3-2021
  • Online
  • All submissions will be reviewed by at least three program Committee members. The submission...
View more
Online

Dec-1-2021 | 12:00am

8th International Conference on Information M...

Online conference

United States

ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO)
  • 09:00am Oct-5-2021
         05:00pm Oct-9-2021
  • Virtual
  • Dear colleagues, We are excited to announce the inaugural ACM Conference on Equity and Access in Al...
View more
Online

Oct-5-2021 | 09:00am

ACM Conference on Equity and Access in Algori...

Mechanism Design for Social Good (MD4SG)

United States

            Load more