Artwork

Content provided by Debra J. Farber (Shifting Privacy Left). All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Debra J. Farber (Shifting Privacy Left) or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.
Player FM - Podcast App
Go offline with the Player FM app!

S2E13: Diving Deep into Fully Homomorphic Encryption (FHE) with Kurt R. Rohloff (Duality Technologies)

48:43
 
Share
 

Manage episode 421035584 series 3407760
Content provided by Debra J. Farber (Shifting Privacy Left). All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Debra J. Farber (Shifting Privacy Left) or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.

I am delighted to welcome this week’s guest, Kurt Rohloff. Kurt is the CTO and Co-Founder of Duality Technologies, a privacy tech company that enables organizations to leverage data across their ecosystem and generate joint insights for better business while preserving privacy. Kurt was also Co-Founder of the OpenFHE Homomorphic Encryption Software Library that enables practical and usable privacy and collaborative data analytics.
He's successfully led teams that are developing, transitioning, and applying first-in-the-world technology capabilities for both the Department of Defense as well as for commercial use. Kurt specializes in generating, developing, and commercializing innovative secure computing technologies with a focus on privacy and AI/ML at scale. In this episode, we discuss use cases for leveraging Fully Homomorphic Encryption (FHE) and other PETs.
In a previous episode, we spoke about federated learning; and in this episode, we learn how to achieve secure federated learning using fully homomorphic encryption (FHE) techniques.

Kurt has been focused on and supported homomorphic encryption since it was first discovered, including his involvement in one of the seminal projects, funded by DARPA, where he ran an implementation team, called PROCEED.

FHE, as opposed to other kinds of privacy technologies, is more general and malleable. As each organization has different needs when it comes to data collaboration, Duality Technologies offers three separate models for collaboration, which enable organizations to secure sensitive data while still allowing different types of sharing.

Topics Covered:

  • How companies can gain utility from a dataset while protecting the privacy of individuals or entities
  • How FHEs help with fraud prevention, How FHEs help with fraud prevention, secure investigations, real-world evidence & genome-wide association studies
  • Use cases for the three collaboration models Duality offers: Single Data Set, Horizontal Data Analysis, and Vertical Data Analysis
  • Comparison & trade-offs involved between federated learning and homomorphic encryption
  • Proliferation of FHE Standards
  • OpenFHE.org, the leading open source library for implementations of fully homomorphic encryption protocols

Resources Mentioned:

Guest Info:

Send us a Text Message.

Privado.ai
Privacy assurance at the speed of product development. Get instant visibility w/ privacy code scans.
Shifting Privacy Left Media
Where privacy engineers gather, share, & learn
Buzzsprout - Launch your podcast
Disclaimer: This post contains affiliate links. If you make a purchase, I may receive a commission at no extra cost to you.
Copyright © 2022 - 2024 Principled LLC. All rights reserved.

  continue reading

Chapters

1. S2E13: Diving Deep into Fully Homomorphic Encryption (FHE) with Kurt R. Rohloff (Duality Technologies) (00:00:00)

2. Introducting Kurt R. Rohloff, CTO & Co-Founder of Duality Technologies (00:01:15)

3. How and why companies have been struggling to find ways to conduct analytics while preserving privacy (00:02:28)

4. Introducing 'homomorphic encryption' (00:04:27)

5. Duality Collaboration Model 1: Analytics of a single data set (00:06:07)

6. Duality Collaboration Model 2: Analytics of a union of datasets (Horizontal Data Analysis) (00:07:55)

7. Duality Collaboration Model 3: Analytics of join datasets (Vertical Data Analysis) (00:11:54)

8. Comparing 'federated learning' to 'federated analysis' using FHE (00:13:58)

9. Tradeoffs involved with FHE (00:16:16)

10. Kurt describes his work with DARPA's PROCEED program using FHE a decade ago (00:18:49)

11. FHE Use Case 1: financial services - fraud prevention (00:24:48)

12. FHE Use Case 2: government - secure investigations (00:28:26)

13. FHE Use Cases 3 & 4: real-world evidence and genome-wide association studies (00:31:30)

14. Proliferation of FHE Standards (00:34:25)

15. Kurt discusses OpenFHE.org, the leading open source library for implementations of fully homomorphic encryption protocols (00:41:28)

16. Resources and conferences that Kurt recommends to privacy technologists and data scientists who want to learn more about this space (00:44:16)

63 episodes

Artwork
iconShare
 
Manage episode 421035584 series 3407760
Content provided by Debra J. Farber (Shifting Privacy Left). All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Debra J. Farber (Shifting Privacy Left) or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.

I am delighted to welcome this week’s guest, Kurt Rohloff. Kurt is the CTO and Co-Founder of Duality Technologies, a privacy tech company that enables organizations to leverage data across their ecosystem and generate joint insights for better business while preserving privacy. Kurt was also Co-Founder of the OpenFHE Homomorphic Encryption Software Library that enables practical and usable privacy and collaborative data analytics.
He's successfully led teams that are developing, transitioning, and applying first-in-the-world technology capabilities for both the Department of Defense as well as for commercial use. Kurt specializes in generating, developing, and commercializing innovative secure computing technologies with a focus on privacy and AI/ML at scale. In this episode, we discuss use cases for leveraging Fully Homomorphic Encryption (FHE) and other PETs.
In a previous episode, we spoke about federated learning; and in this episode, we learn how to achieve secure federated learning using fully homomorphic encryption (FHE) techniques.

Kurt has been focused on and supported homomorphic encryption since it was first discovered, including his involvement in one of the seminal projects, funded by DARPA, where he ran an implementation team, called PROCEED.

FHE, as opposed to other kinds of privacy technologies, is more general and malleable. As each organization has different needs when it comes to data collaboration, Duality Technologies offers three separate models for collaboration, which enable organizations to secure sensitive data while still allowing different types of sharing.

Topics Covered:

  • How companies can gain utility from a dataset while protecting the privacy of individuals or entities
  • How FHEs help with fraud prevention, How FHEs help with fraud prevention, secure investigations, real-world evidence & genome-wide association studies
  • Use cases for the three collaboration models Duality offers: Single Data Set, Horizontal Data Analysis, and Vertical Data Analysis
  • Comparison & trade-offs involved between federated learning and homomorphic encryption
  • Proliferation of FHE Standards
  • OpenFHE.org, the leading open source library for implementations of fully homomorphic encryption protocols

Resources Mentioned:

Guest Info:

Send us a Text Message.

Privado.ai
Privacy assurance at the speed of product development. Get instant visibility w/ privacy code scans.
Shifting Privacy Left Media
Where privacy engineers gather, share, & learn
Buzzsprout - Launch your podcast
Disclaimer: This post contains affiliate links. If you make a purchase, I may receive a commission at no extra cost to you.
Copyright © 2022 - 2024 Principled LLC. All rights reserved.

  continue reading

Chapters

1. S2E13: Diving Deep into Fully Homomorphic Encryption (FHE) with Kurt R. Rohloff (Duality Technologies) (00:00:00)

2. Introducting Kurt R. Rohloff, CTO & Co-Founder of Duality Technologies (00:01:15)

3. How and why companies have been struggling to find ways to conduct analytics while preserving privacy (00:02:28)

4. Introducing 'homomorphic encryption' (00:04:27)

5. Duality Collaboration Model 1: Analytics of a single data set (00:06:07)

6. Duality Collaboration Model 2: Analytics of a union of datasets (Horizontal Data Analysis) (00:07:55)

7. Duality Collaboration Model 3: Analytics of join datasets (Vertical Data Analysis) (00:11:54)

8. Comparing 'federated learning' to 'federated analysis' using FHE (00:13:58)

9. Tradeoffs involved with FHE (00:16:16)

10. Kurt describes his work with DARPA's PROCEED program using FHE a decade ago (00:18:49)

11. FHE Use Case 1: financial services - fraud prevention (00:24:48)

12. FHE Use Case 2: government - secure investigations (00:28:26)

13. FHE Use Cases 3 & 4: real-world evidence and genome-wide association studies (00:31:30)

14. Proliferation of FHE Standards (00:34:25)

15. Kurt discusses OpenFHE.org, the leading open source library for implementations of fully homomorphic encryption protocols (00:41:28)

16. Resources and conferences that Kurt recommends to privacy technologists and data scientists who want to learn more about this space (00:44:16)

63 episodes

所有剧集

×
 
Loading …

Welcome to Player FM!

Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.

 

Quick Reference Guide