Privacy-Preserving Decentralized Data Science with Andrew Trask - TWiML Talk #241
Published:Mar 21, 2019 16:27
•1 min read
•Practical AI
Analysis
This article highlights a discussion with Andrew Trask, a leader in privacy-preserving AI. It focuses on OpenMined, an open-source project dedicated to secure and ethical AI development. The core topics include decentralized data science, differential privacy, and secure multi-party computation. The article emphasizes the importance of these technologies in creating AI systems that protect user privacy while still enabling valuable insights from data. The interview likely delves into the practical applications and challenges of implementing these techniques.
Key Takeaways
- •The article discusses privacy-preserving techniques in AI.
- •It highlights the work of Andrew Trask and the OpenMined project.
- •Key technologies mentioned include Differential Privacy and Secure Multi-Party Computation.
Reference
“We dig into why OpenMined is important, exploring some of the basic research and technologies supporting Private, Decentralized Data Science, including ideas such as Differential Privacy,and Secure Multi-Party Computation.”