PPML 2020

August 16, 2020

 

 

Santa Barbara, USA

Affiliated Event: The 2nd Privacy-Preserving Machine Learning Workshop 2020

About

Artificial intelligence is progressing rapidly. Systems based on machine learning algorithms approach and sometimes even exceed the abilities of human experts. Applications of machine learning involve almost every aspect of our lives, from health care and DNA sequence classification, to financial markets, computer networks and many more. Machine learning algorithms perform better when being exposed to more and more data, but such data is not always accessible due to privacy constraints. Can we train machine learning algorithms on confidential data without ever being exposed to it? Can my model classify your sample without ever seeing it?

The workshop aims to strengthen collaborations among the machine learning and cryptography communities. The scope includes privacy preserving techniques for training, inference, and disclosure. The workshop will consist of few invited talks, together with contributed talks.

Date of Event

August 16, 2020 (Sunday)

Location

Zoom. A link to the stream will be given later.

Program

The program will consist of several invited speakers as well as contributed talks. Please see the call for contributed talks below.

(Confirmed) Invited Speakers

  • Shafi Goldwasser (UC Berkeley)
  • Mohammad Mahmoody (University of Virginia)
  • Ilya Mironov (Facebook AI)
  • Ramesh Raskar (MIT Media Lab)

Call for Contributed Talks

We encourage submissions exploring a range of techniques for privacy preserving machine learning, including, but not limited to:

  • Multiparty computation
  • Homomorphic encryption
  • Differential privacy
  • Adversarial machine learning
  • Model stealing
  • Fairness and accountability

Submission site: https://secure.iacr.org/websubrev/privAI2020/submit/

Submission deadline: August 2nd, 2020.

Notifications: August 6th, 2020.

Submissions must comply with the following rules:

  • Submissions can be full papers, abstracts (maximum 2 pages), or the expected presentation slides.
  • Submissions must be non-anonymous and must clearly specify which author will give the talk.
  • The submission should provide sufficient detail to explain what the talk will be about.
  • As the workshop does not have formal proceedings, we accept contributed talk proposals which correspond to papers that are under submission or already published elsewhere (parallel submissions are allowed).

The committee will follow COI standards according to the IACR policy. Contributed Talks Committee members are allowed to submit as well.

Contributed Talks Committee

  • Adi Akavia (Haifa University)
  • Gilad Asharov (Bar-Ilan University)
  • Carsten Baum (Aarhus University)
  • Vipul Goyal (Carnegie Mellon University)
  • Rafail Ostrovsky (UCLA)
  • Antigoni Polychroniadou (JP Morgan AI Research)
  • Gil Segev (Hebrew University)
  • Muthu Venkitasubramaniam (University of Rochester)

Organizers

Contact email: CRYPTO.PPML.2020@gmail.com