Keynote: Unlocking exabytes of training data through privacy preserving machine learning

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=N3SmCedM1Zk


Duration: 22:13
138 views
0

Speaker: Jim Kleewein, Technical Fellow, Microsoft

Data is the lifeblood of AI and machine learning. The better the model, and the better the data that model is trained on, the better the outcome. Today’s models are big and powerful, capable of outcomes deemed miraculous or impossible only a few years ago, yet they are generally only trained using relatively small corpuses. Pause for a second and imagine what could be accomplished with order of magnitude more data. It is staggering. Join Jim Kleewein, Technical Fellow in Office 365, to learn more about use of private data in training public models. We’ll explore why private data is seldom used, the barriers to unlocking exabytes of new training data and the requirements a solution must fulfill, and why research into PPML, privacy preserving machine learning, is essential to keep driving the state of the art further.

Learn more about the 2021 Microsoft Research Summit: https://Aka.ms/researchsummit



Other Videos By Microsoft Research


2022-02-08Research talk: Causal ML and business
2022-02-08Research talk: Challenges and opportunities in causal machine learning
2022-02-08Opening remarks: Causal Machine Learning
2022-02-08Closing remarks: The Future of Privacy and Security
2022-02-08Demo: Generating formally proven low-level parsers with EverParse
2022-02-08Demo: EverParse: Automatic generation of formally verified secure parsers for cloud integrity
2022-02-08Research talk: DARPA SafeDocs: an approach to secure parsing and information interchange formats
2022-02-08Research talk: Privacy in machine learning research at Microsoft
2022-02-08Research talk: Towards bridging between legal and technical approaches to data protection
2022-02-08Research talk: Building towards a responsible data economy
2022-02-08Keynote: Unlocking exabytes of training data through privacy preserving machine learning
2022-02-08Closing remarks: Responsible AI
2022-02-08Opening remarks: The Future of Privacy and Security
2022-02-08Tutorial: Create human-centered AI with the Human-AI eXperience (HAX) Toolkit
2022-02-08Panel: Maximizing benefits and minimizing harms with language technologies
2022-02-08Lightning talks: Advances in fairness in AI: New directions
2022-02-08Closing remarks: Tech for resilient communities
2022-02-08Lightning talks: Advances in fairness in AI: From research to practice
2022-02-08Panel: Content moderation beyond the ban: Reducing toxic, misleading, and low-quality content
2022-02-08Technology demo: Using technology to combat human trafficking
2022-02-08Technology demo: Project Eclipse: Hyperlocal air quality monitoring for cities


Tags:
security
user privacy
future of security
future of privacy
trust in technology
system integrity
privacy preserving machine learning
election integrity
secure parsing technology
communication protocols for systems
microsoft research summit