Privacy-preserving Analytics and Machine Learning with Differential Privacy

To access this webinar, please register here: https://aiplus.odsc.com/courses/privacy-preserving-analytics-and-machine-learning-with-differential-privacy

Topic: Privacy-preserving Analytics and Machine Learning with Differential Privacy

Speaker#1: Andreas Kopp, Digital Advisor for AI Solutions, Microsoft
https://www.linkedin.com/in/andreas-kopp-1947183/

As a Microsoft Digital Advisor, Andreas Kopp advises Enterprise customers on the planning and implementation of digital business solutions. His focus is on applied business AI solutions, including medical imaging and fraud detection.

Speaker#2: Sarah Bird, Principal Program Manager, Microsoft
https://www.linkedin.com/in/slbird/

Sarah is an active member of the Microsoft AETHER committee, where she works to develop and drive company-wide adoption of responsible AI principles, best practices, and technologies. Sarah was one of the founding researchers in the Microsoft FATE research group and prior to joining Microsoft worked on AI fairness in Facebook.

Speaker#3: Lucas Rosenblatt, ML Engineer (MAIDAP) at Microsoft
https://www.linkedin.com/in/lucas-rosenblatt-660687126/

He works in the space of responsible AI around privacy and fairness, and has contributed differentially private synthesizers to the Smartnoise toolkit. You can read about some of his work in a paper he and the team published on the subject: https://arxiv.org/abs/2011.05537

Abstract:
The COVID-19 pandemic demonstrates the tremendous importance of data for research, cause analysis, government action, and medical progress. However, for understandable data protection considerations,

individuals and decision-makers are often very reluctant to share personal or sensitive data. To ensure sustainable progress, we need new practices that enable insights from personal data while reliably protecting individuals' privacy.

Invented by Microsoft Research and associates, differential privacy is the emerging gold standard for protecting data in applications like preparing and publishing statistical analyses. Differential privacy provides a mathematically measurable privacy guarantee to individuals by adding a carefully tuned amount of statistical noise to sensitive data. It promises significantly higher privacy protection levels than commonly used disclosure limitation practices like data anonymization.

Join our demo-intensive session to learn about:

• What differential privacy is and how it works
• Microsoft's and Harvard's OpenDP initiative and the SmartNoise system
• Using SmartNoise to protect sensitive data against privacy attacks
• How to create differentially private synthetic data using the new SmartNoise synthesizers
• Performing analytics, machine learning including deep learning on sensitive data using differential privacy
• The trade-off between privacy guarantee and accuracy of analytical results
• How to engage in our Early Adopter program

[March] Get your Virtual ODSC East 2021 pass with 50% OFF - http://bit.ly/3aRHtlt

[June] Get your Virtual ODSC Europe 2021 pass with 75% OFF - http://bit.ly/38z7q84

ODSC Links:
• Get free access to more talks/trainings like this at AI+ Training platform:
https://aiplus.odsc.com/
• Facebook: https://www.facebook.com/OPENDATASCI
• Twitter: https://twitter.com/odsc & @odsc
• LinkedIn: https://www.linkedin.com/company/open-data-science
• Slack Channel: http://bit.ly/2RkOf9l
• East Conference March 30th - April 1st: https://odsc.com/boston/
• Europe Conference June 8th - 10th: https://odsc.com/europe/
• West Conference November 15th - 18th: https://odsc.com/california/
• Code of conduct: https://odsc.com/code-of-conduct/