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 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:
We think it will be very valuable to have a forum to unify different perspectives and start a discussion about the relative merits of each approach. The workshop will also serve as a venue for networking people from different communities interested in this problem, and hopefully foster fruitful long-term collaboration.
Submission deadline: October 8, 2018 (11:59pm AoE)
Notification of acceptance: November 1, 2018
Workshop: December 8, 2018
Submissions in the form of extended abstracts must be at most 4 pages long (not including references) and adhere to the NIPS format. We do accept submissions of work recently published or currently under review. Submissions should be anonymized. The workshop will not have formal proceedings, but authors of accepted abstracts can choose to have a link to arxiv or a pdf published on the workshop webpage.
We can offer the opportunity to purchase a NIPS registration to one author of each accepted paper. Currently, we only have the information that is available at the Workshop FAQ and will provide updates as soon as we know more.
A limited number of travel grants will be available to help partially cover the expenses of authors of accepted papers. We might not be able to provide awards to all applicants, in which case awards will be determined by the organizers based on the application material.
Application details follow shortly.