Machine learning provides the foundation for many smart applications. Therefore, a large amount of partly private data is captured by sensors, pre-processed by data stream systems and stored in databases. Such applications are a substantial benefit for the user. Yet, there is a growing concern on the part of users regarding the large-scale processing of private data. In addition, new regulations such as the General Data Protection Regulation (GDPR) restrict this kind of data processing even further. The PriMaL Special Track concerns with novel approaches that guarantee privacy in machine learning applications without restricting their utility unnecessarily.
********************************************************************************************************************
Special Track PriMaL Privacy for High-Utility Machine Learning
http://www.iaria.org/conferences2019/filesSECURWARE19/PriMal.pdf
along with
SECURWARE 2019, The Thirteenth International Conference on Emerging Security Information, Systems and Technologies October 27, 2019 to October 31, 2019 - Nice, France
http://www.iaria.org/conferences2019/SECURWARE19.html
********************************************************************************************************************
Call for Papers:
=============
Machine learning and data mining provide the foundation for a vast number of smart applications today. For this purpose, a large amount of partly private data is captured by sensors, pre-processed by data stream systems and stored in databases. Machine learning and data mining approaches then learn models from these data. By applying these models to real time data, smart applications are able to predict and adapt to future requirements. Such applications are a substantial benefit for the user. However, to enable smart applications, a large amount of data is required in the first place. Only if the data quality is sufficient, accurate models can be learned and sound predictions can be made. Yet, there is a growing concern on the part of users regarding the large-scale processing of private data. In addition, new regulations such as the General Data Protection Regulation (GDPR) restrict this kind of data processing even further. Today's data privacy approaches affect data quality and data quantity severely so that the utility of machine learning and data mining suffers sustainably.
The PriMaL Special Track, therefore, concerns with novel approaches that guarantee privacy in machine learning applications without restricting their utility unnecessarily. This track aims at providing a forum to discuss recent advancements, exchange ideas and share experiences on new issues and challenges in the context of privacy for high-utility machine learning.
Topics of interest include (but are not limited to):
========================================
• Novel privacy approaches for machine learning applications
• Architectures supporting privacy-aware machine learning
• Privacy-preserving model generation
• Differential privacy
• Misuse of machine learning
• Understandable preparation of decisions based on machine learning
• GDPR-conform machine learning approaches
• Experience reports on privacy-aware machine learning
Important Deadlines:
====================
• Inform the Chair: As soon as you decide to contribute
• Submission: August 31
• Notification: September 20
• Registration: September 30
• Camera-ready: September 30
• Conference: October 27 – 31
Contribution Types:
===================
• Regular papers [in the proceedings, digital library]
• Short papers (work in progress) [in the proceedings, digital library]
• Posters: two pages [in the proceedings, digital library]
• Posters: slide only [slide-deck posted on www.iaria.org]
• Presentations: slide only [slide-deck posted on www.iaria.org]
• Demos: two pages [posted on www.iaria.org]
Paper Format:
=============
• See: http://www.iaria.org/format.html [both LaTex and .doc templates]
• Final author manuscripts must not exceeding 6 pages; max 4 extra pages allowed at additional cost
• For detailed formatting instructions see http://www.iaria.org/instructions.html#format
• Before submission, please check and comply with the editorial rules: http://www.iaria.org/editorialrules.html
• More information on camera ready preparations will be posted after the paper notifications are sent out
Publications:
=============
• Extended versions of selected papers will be published in IARIA Journals: http://www.iariajournals.org
• Print proceedings will be available via Curran Associates, Inc.: http://www.proceedings.com/9769.html
• Articles will be archived in the free access ThinkMind Digital Library: http://www.thinkmind.org
=================
https://www.iariasubmit.org/conferences/submit/newcontribution.php?event=SECURWARE+2019+Special
Please select Track Preference as PriMaL
Registration:
=============
• Each accepted paper needs at least one full registration, before the camera-ready manuscript can be included in the proceedings
• Registration fees are available at http://www.iaria.org/registration.html
=========
• Christoph Stach: Christoph.Stach@ipvs.uni-stuttgart.de
• SECURWARE Logistics: steve@iaria.org
Sign up and follow your favorite conferences.