PSML 2017 - Workshop on Private and Secure Machine Learning 2017

There are two complementary approaches to private and secure machine learning: differential privacy can guarantee privacy of the subjects of the training data with respect to the output of a differentially private learning algorithm, while cryptographic approaches can guarantee secure operation of the learning process in a potentially distributed environment. The aim of this workshop is to discuss the most recent results in this very rapidly progressing and exciting field, and to bring together researchers from both private and secure machine learning, to stimulate interactions to advance either perspective or to combine them.
IMPORTANT DATES
* Submission Date: 26 May 2017
* Notification of Acceptance: 19 June 2017
* Workshop date: 10 or 11 August 2017
CALL FOR CONTRIBUTIONS
We invite submissions of abstracts for talks and posters at PSML2017 on all aspects of private and secure ML. The abstracts should be 300-600 words long. The program committee will select several submitted abstracts for 20-minute talks. PSML2017 will consider submissions of both previously published and unpublished work. Accepted abstracts will be published on the workshop website.
We look forward for submissions that are novel, exciting and that appeal to the wider community. For more details see:
https://sites.google.com/view/psml/
Please submit your contributions at
https://www.easychair.org/conferences/?conf=psml20...
ORGANIZERS:
Antti Honkela (http://www.hiit.fi/u/ahonkela/)
Kana Shimizu (https://iskana.github.io/web/)
Samuel Kaski (https://users.ics.aalto.fi/sami/)