633: Responsible Decentralized Intelligence
This week's episode is all about Responsible Decentralized Intelligence as award-winning professor and tech entrepreneur, Dawn Song, joins Jon Krohn to help us explore this exciting topic in-depth.
This episode is brought to you by Iterative (iterative.ai), your mission control center for machine learning. Interested in sponsoring a SuperDataScience Podcast episode? Visit JonKrohn.com/podcast for sponsorship information.
In this episode you will learn:
• What is decentralized intelligence? [3:46]
• Dawn’s Responsible Data Economy collaboration with Meta AI [11:31]
• How homomorphic encryption, differential privacy, and multi-party computation can work together [16:22]
• How PrivateSQL makes differential privacy easy to use [22:54]
• The relationship between deep learning and federated learning [37:55]
• What is a responsible data economy [42:13]
Additional materials: www.superdatascience.com/633
AI and the Responsible Data Economy with Dawn Song - #403
Today we’re joined by Professor of Computer Science at UC Berkeley, Dawn Song. Dawn’s research is centered at the intersection of AI, deep learning, security, and privacy. She’s currently focused on bringing these disciplines together with her startup, Oasis Labs.
In our conversation, we explore their goals of building a ‘platform for a responsible data economy,’ which would combine techniques like differential privacy, blockchain, and homomorphic encryption. The platform would give consumers more control of their data, and enable businesses to better utilize data in a privacy-preserving and responsible way.
We also discuss how to privatize and anonymize data in language models like GPT-3, real-world examples of adversarial attacks and how to train against them, her work on program synthesis to get towards AGI, and her work on privatizing coronavirus contact tracing data.
The complete show notes for this episode can be found twimlai.com/go/403.
#95 – Dawn Song: Adversarial Machine Learning and Computer Security
Dawn Song is a professor of computer science at UC Berkeley with research interests in security, most recently with a focus on the intersection between computer security and machine learning.
Support this podcast by signing up with these sponsors:
– Cash App – use code “LexPodcast” and download:
– Cash App (App Store): https://apple.co/2sPrUHe
– Cash App (Google Play): https://bit.ly/2MlvP5w
EPISODE LINKS:
Dawn’s Twitter: https://twitter.com/dawnsongtweets
Dawn’s Website: https://people.eecs.berkeley.edu/~dawnsong/
Oasis Labs: https://www.oasislabs.com
This conversation is part of the Artificial Intelligence podcast. If you would like to get more information about this podcast go to https://lexfridman.com/ai or connect with @lexfridman on Twitter, LinkedIn, Facebook, Medium, or YouTube where you can watch the video versions of these conversations. If you enjoy the podcast, please rate it 5 stars on Apple Podcasts, follow on Spotify, or support it on Patreon.
Here’s the outline of the episode. On some podcast players you should be able to click the timestamp to jump to that time.
OUTLINE:
00:00 – Introduction
01:53 – Will software always have security vulnerabilities?
09:06 – Human are the weakest link in security
16:50 – Adversarial machine learning
51:27 – Adversarial attacks on Tesla Autopilot and self-driving cars
57:33 – Privacy attacks
1:05:47 – Ownership of data
1:22:13 – Blockchain and cryptocurrency
1:32:13 – Program synthesis
1:44:57 – A journey from physics to computer science
1:56:03 – US and China
1:58:19 – Transformative moment
2:00:02 – Meaning of life
Episode 25 - Dawn Song
This week, I talk to Dawn Song, one of the world's foremost experts in computer security, about her vision of a new paradigm in which people control their data and are compensated for its use by corporations. Dawn, a professor at the University of California, Berkeley, has recently launched a company, Oasis Labs, which is building a platform that brings together the immutability of blockchain and the privacy of secure enclaves to give data owners the ability to control their data.