SlideShare uma empresa Scribd logo
© 2024 AI Singapore
Privacy Enhancing
Technologies for AI
Mark Choo
17 April 2024
© 2024 AI Singapore
The Future of Federated Learning
Is there a case for Federated Learning(FL)?
Since 2016, there are more than 3,900 papers on FL being
published to arXiv alone.
In recent years, there is a growing number of investments
made into FL by the big tech companies.
In March 2023, OECD published a paper on
Emerging Privacy Enhancing Technologies(PET)
and recognize FL as 1 of the 4 PETs categories.
This sets the stage for FL to be adopted for data
privacy protection as part of Privacy Design.
https://www.oecd.org/publications/emerging-privacy-
enhancing-technologies-bf121be4-en.htm
© 2024 AI Singapore
How federated learning works?
1. A group of parties (with local data) come together and form a network, with the common goal to
train a model together.
Party
A
Data
Party
B
Data
Party
C
Data
© 2024 AI Singapore
How federated learning works?
2. The Trusted Third Party (TTP) acts as the coordinator (it does not contribute data). It sends this
model to all the other participating parties. This model would serve as a baseline for each individual
party to start training with only local data.
Party
A
Data
Party
B
Data
Party
C
Data
Trusted
Third
Party
Model
© 2024 AI Singapore
How federated learning works?
3. Each participating party will start to train the given model with its own local data.
Party
A
Data
Party
B
Data
Party
C
Data
Trusted
Third
Party
Model
Model
Model
Model
W
© 2024 AI Singapore
How federated learning works?
3. Periodically, all parties send their learning (weights, gradients, losses, etc.) to the TTP. NO local
data is ever exposed.
Party
A
Data
Party
B
Data
Party
C
Data
Trusted
Third
Party
Model
Model
Model
Model
W
© 2024 AI Singapore
How federated learning works?
4. The TTP then aggregates the new learnings from the parties and continues to improve the shared
model.
Party
A
Data
Party
B
Data
Party
C
Data
Trusted
Third
Party
Model
Model
Model
Model
W
© 2024 AI Singapore
How federated learning works?
5. The new shared model is again sent back to the participating parties and the same cycle repeats
again and again. With each iteration, the shared model maintained by the TTP gets better.
Party
A
Data
Party
B
Data
Party
C
Data
Trusted
Third
Party
Model
Model
Model
Model
No raw
data is
received
© 2024 AI Singapore
Operational Impact of Data Collaboration
What is the typical organization structure during Data Centralization?
Raw
Data
Raw
Data
Raw
Data
Raw
Data
Data Processor
Data Controller
Organization 1
Data Processor
Data Controller
Organization 2
Third Party Organization
Consolidator
Storage
© 2024 AI Singapore
Operational Impact of Data Collaboration
Structure 1: Organization is both the Data Controller and Data Processor
Raw
Data
Raw
Data
Data Processor
Data Controller
Organization 1
Consolidator
Storage
Organization 1 controls the full workflow
Organization 1 of the federated grid is ultimately bounded by legalities
regarding raw data since users’ personal data is
• Processed
• Stored
• Organised
• Collected
• Disseminated
Intra-organizational workflow
• Regulations are between departments
• Relatively easier/feasible to get access since contracts/request
workflows/audits are all consistent within the organisation
Data is often immobile due to data lakes
© 2024 AI Singapore
Operational Impact of Data Collaboration
Structure 2: Organization is the Data Controller and Third Party is the Data Processor
Raw
Data
Raw
Data
Data Processor
Data Controller
Organization 2
Third Party Organization
Consolidator
Storage
Inter-Organization Efforts
Third Party processes the raw data when it receives operations
from orchestrator, and is bounded by legalities regarding raw data
since users’ personal data is
• Processed
• Stored
• Organised
Organization 2 controls the ingestion and usage of the raw data
and hence is bounded by legalities regarding raw data since users’
personal data is
• Collected
• Stored
• Organised
• Disseminated
© 2024 AI Singapore
A Different Structure for Data Collaboration
Federated Grid to Truly Retain Control of Private and Proprietary Data
Raw
Data
Raw
Data
Federated Node
Data Controller
Organization 1
Federated Node
Data Controller
Organization 2
Third Party Organization
Orchestrator
Analytics | Mathematical Weights Analytics | Mathematical Weights
Federated Grid
© 2024 AI Singapore
Federated Learning Beyond Privacy
What other problems can Federated Learning solve?
Data Immobility
● Volume of Data can cause the duplication and transfer of data for centralized model
training to be inefficient and expensive.
○ For e.g., Medical Images can be very large even at individual level.
○ For e.g., Financial Transaction Data where the business nature is data hungry.
Collaborative AI
● Veracity of Data can be improved because a party’s data may not contain the whole
picture, but multiple party’s data can potentially improve the quality of the data
○ For e.g., Multiple banks coming together to build a global fraud detection model.
● Value & Variety of Data can be exploited more.
○ For e.g., Supermarket and Hospital coming together to build a model to identify
someone at risk of getting diabetes.
Images generated with Microsoft Co-Pilot
© 2024 AI Singapore
Unlock Data with Federated Learning
How can companies collaborate with their datasets?
Sample
ID
Sample
ID
Features
Features
Overlapped
Features Set
(red box)
Labels
Dataset from A
Dataset from B
Labels
Sample
ID
Sample
ID
Features
Features
Overlapped
Sample Set
(redbox)
Labels
Dataset from A
Dataset from B
Vertical Federated Learning
Labels
Horizontal Federated Learning
● A and B are from different industry and the dataset use case
is likely different.
● There is an overlap of Sample set (row-wise).
● Vertical FL allows training of a global model with a larger
amount of data features using the overlapped sample set.
● A and B are likely in the same industry and the dataset
use case is the same with overlapping data features.
● This allow horizontal FL to train a global model with the
enlarged overlapped features set. (red box)
● In other words, this means training a larger number of
samples with the overlapped data features.
© 2024 AI Singapore
Centralized vs Federated Collaboration
Cost Analysis of Centralized Collaborative AI vs Federated Learning Collaboration
During training collaboration between different parties, the cost of centralization data can
get hefty due to the data transfer and duplication of storage.
* Data are taken from commercial cloud provider’s public pricing calculator
* Data transfer is within the same cloud provider and between Asia region
© 2024 AI Singapore
Centralized vs Federated Collaboration
Cost Analysis of Centralized Collaborative AI vs Federated Learning Collaboration
16 GB 161 GB
800 GB
Since the collaborator’s cost is linear, the cost of central collaboration is approximately 5 times more than if
the collaborator trains on its own. (No data duplication and no data transfer)
Adopting Federated Learning as a collaboration method reduces the cost of collaboration as the dataset
size scales.
© 2024 AI Singapore
Federated Learning for Public Good
There is a lot more to learn if we can come together
Individual organizations can only solve public good problem
with their own data. But with data collaboration, we are
increasing the solution space and benefit.
In the example, each organization has 100 PB of data and
through collaboration each organization now has 300 PB of
data for learning.
The total benefit will be 900 PB of data for public good.
© 2024 AI Singapore
Federated Learning for Public Good
There is a lot more to learn if we can come together
There is a scaling effect with the number of participants
coming together to share knowledge.
The more data we share, the more good we can
potentially do.
© 2024 AI Singapore
AISG 100E Federated Learning Projects
Examples of Federated Learning Use Case
Federated Learning for ICU
in-hospital mortality
prediction
https://link.springer.com/chapter/10.1
007/978-3-030-63076-8_18
A large multi-centre critical care
database made available by Philips
Healthcare in partnership with the
MIT Laboratory for Computational
Physiology were used.
Data is anonymised and cleansed.
Three hospitals with the most
number of ICU stays, and most
complete data were kept.
A mortality prediction model was built
for the research paper.
Federated Predictive
Maintenance for Telemetry
Log Data
A Global Data Infrastructure Service
Provider wanted to improve the
availability of services and minimize
disruption for their customers by
predicting when maintenance are
required.
However, the telemetry log data are
housed at customer sites and
centralizing the data are expensive and
faces regulatory hurdles on data
residency.
The FL team implemented a Federated
Learning solution that allows model
customization.
Federated Image
Segmentation on Large
OCT Scans
A Global Pharmaceutical Company faces data
privacy hurdles and high cost of data
centralization for research.
Medical images are highly sensitive and can
be very large in size for even centralized ML
training.
The team customize & optimize Synergos with
new engineering features that not only
orchestrate image segmentation in a
federated setting, but also to handle large
medical data.
© 2024 AI Singapore
Thank you
www.aisingapore.org

Mais conteúdo relacionado

Semelhante a Apidays Singapore 2024 - Privacy Enhancing Technologies for AI by Mark Choo, Federated Learning - AI Singapore

Data warehouse,data mining & Big Data
Data warehouse,data mining & Big DataData warehouse,data mining & Big Data
Data warehouse,data mining & Big DataRavinder Kamboj
 
Search Engine Scrapper
Search Engine ScrapperSearch Engine Scrapper
Search Engine ScrapperIRJET Journal
 
Using Ontology to Capture Supply Chain Code Halos
Using Ontology to Capture Supply Chain Code HalosUsing Ontology to Capture Supply Chain Code Halos
Using Ontology to Capture Supply Chain Code HalosCognizant
 
Fathoming Data for Competitive Advantage
Fathoming Data for Competitive AdvantageFathoming Data for Competitive Advantage
Fathoming Data for Competitive AdvantageCapgemini
 
Rebooting IT Infrastructure for the Digital Age
Rebooting IT Infrastructure for the Digital AgeRebooting IT Infrastructure for the Digital Age
Rebooting IT Infrastructure for the Digital AgeCapgemini
 
Cloud Based Virtual Organization
Cloud Based Virtual OrganizationCloud Based Virtual Organization
Cloud Based Virtual OrganizationIRJET Journal
 
A blueprint for data in a multicloud world
A blueprint for data in a multicloud worldA blueprint for data in a multicloud world
A blueprint for data in a multicloud worldMehdi Charafeddine
 
Using Information Technology to Engage in Electronic Commerce
Using Information Technology to Engage in Electronic CommerceUsing Information Technology to Engage in Electronic Commerce
Using Information Technology to Engage in Electronic CommerceElla Mae Ayen
 
Electronic Commerce
Electronic CommerceElectronic Commerce
Electronic Commerceellamee27
 
Data Pioneers - Roland Haeve (Atos Nederland) - Big data in organisaties
Data Pioneers - Roland Haeve (Atos Nederland) - Big data in organisatiesData Pioneers - Roland Haeve (Atos Nederland) - Big data in organisaties
Data Pioneers - Roland Haeve (Atos Nederland) - Big data in organisatiesMultiscope
 
Active Governance Across the Delta Lake with Alation
Active Governance Across the Delta Lake with AlationActive Governance Across the Delta Lake with Alation
Active Governance Across the Delta Lake with AlationDatabricks
 
Data Wrangling for Big Data Challenges andOpportunities.docx
Data Wrangling for Big Data Challenges andOpportunities.docxData Wrangling for Big Data Challenges andOpportunities.docx
Data Wrangling for Big Data Challenges andOpportunities.docxwhittemorelucilla
 
IRJET- Development and Design of Recommendation System for User Interest Shop...
IRJET- Development and Design of Recommendation System for User Interest Shop...IRJET- Development and Design of Recommendation System for User Interest Shop...
IRJET- Development and Design of Recommendation System for User Interest Shop...IRJET Journal
 
Big Data Analytics in light of Financial Industry
Big Data Analytics in light of Financial Industry Big Data Analytics in light of Financial Industry
Big Data Analytics in light of Financial Industry Capgemini
 
Hybrid IT – A Winning Strategy
Hybrid IT – A Winning StrategyHybrid IT – A Winning Strategy
Hybrid IT – A Winning StrategyOneNeck
 
A Muilt-Keyword Ranked Based Search and Privacy Preservation of Distributed D...
A Muilt-Keyword Ranked Based Search and Privacy Preservation of Distributed D...A Muilt-Keyword Ranked Based Search and Privacy Preservation of Distributed D...
A Muilt-Keyword Ranked Based Search and Privacy Preservation of Distributed D...IRJET Journal
 
A Muilt-Keyword Ranked Based Search and Privacy Preservation of Distributed D...
A Muilt-Keyword Ranked Based Search and Privacy Preservation of Distributed D...A Muilt-Keyword Ranked Based Search and Privacy Preservation of Distributed D...
A Muilt-Keyword Ranked Based Search and Privacy Preservation of Distributed D...IRJET Journal
 
Cloud migration plan1. executive summary ( 1 page)2. scope (
Cloud migration plan1. executive summary ( 1 page)2. scope (Cloud migration plan1. executive summary ( 1 page)2. scope (
Cloud migration plan1. executive summary ( 1 page)2. scope (mehek4
 
Cloud migration plan1. executive summary ( 1 page)2. scope (
Cloud migration plan1. executive summary ( 1 page)2. scope (Cloud migration plan1. executive summary ( 1 page)2. scope (
Cloud migration plan1. executive summary ( 1 page)2. scope (SONU61709
 

Semelhante a Apidays Singapore 2024 - Privacy Enhancing Technologies for AI by Mark Choo, Federated Learning - AI Singapore (20)

Data warehouse,data mining & Big Data
Data warehouse,data mining & Big DataData warehouse,data mining & Big Data
Data warehouse,data mining & Big Data
 
Search Engine Scrapper
Search Engine ScrapperSearch Engine Scrapper
Search Engine Scrapper
 
Using Ontology to Capture Supply Chain Code Halos
Using Ontology to Capture Supply Chain Code HalosUsing Ontology to Capture Supply Chain Code Halos
Using Ontology to Capture Supply Chain Code Halos
 
Neville Fuller
Neville FullerNeville Fuller
Neville Fuller
 
Fathoming Data for Competitive Advantage
Fathoming Data for Competitive AdvantageFathoming Data for Competitive Advantage
Fathoming Data for Competitive Advantage
 
Rebooting IT Infrastructure for the Digital Age
Rebooting IT Infrastructure for the Digital AgeRebooting IT Infrastructure for the Digital Age
Rebooting IT Infrastructure for the Digital Age
 
Cloud Based Virtual Organization
Cloud Based Virtual OrganizationCloud Based Virtual Organization
Cloud Based Virtual Organization
 
A blueprint for data in a multicloud world
A blueprint for data in a multicloud worldA blueprint for data in a multicloud world
A blueprint for data in a multicloud world
 
Using Information Technology to Engage in Electronic Commerce
Using Information Technology to Engage in Electronic CommerceUsing Information Technology to Engage in Electronic Commerce
Using Information Technology to Engage in Electronic Commerce
 
Electronic Commerce
Electronic CommerceElectronic Commerce
Electronic Commerce
 
Data Pioneers - Roland Haeve (Atos Nederland) - Big data in organisaties
Data Pioneers - Roland Haeve (Atos Nederland) - Big data in organisatiesData Pioneers - Roland Haeve (Atos Nederland) - Big data in organisaties
Data Pioneers - Roland Haeve (Atos Nederland) - Big data in organisaties
 
Active Governance Across the Delta Lake with Alation
Active Governance Across the Delta Lake with AlationActive Governance Across the Delta Lake with Alation
Active Governance Across the Delta Lake with Alation
 
Data Wrangling for Big Data Challenges andOpportunities.docx
Data Wrangling for Big Data Challenges andOpportunities.docxData Wrangling for Big Data Challenges andOpportunities.docx
Data Wrangling for Big Data Challenges andOpportunities.docx
 
IRJET- Development and Design of Recommendation System for User Interest Shop...
IRJET- Development and Design of Recommendation System for User Interest Shop...IRJET- Development and Design of Recommendation System for User Interest Shop...
IRJET- Development and Design of Recommendation System for User Interest Shop...
 
Big Data Analytics in light of Financial Industry
Big Data Analytics in light of Financial Industry Big Data Analytics in light of Financial Industry
Big Data Analytics in light of Financial Industry
 
Hybrid IT – A Winning Strategy
Hybrid IT – A Winning StrategyHybrid IT – A Winning Strategy
Hybrid IT – A Winning Strategy
 
A Muilt-Keyword Ranked Based Search and Privacy Preservation of Distributed D...
A Muilt-Keyword Ranked Based Search and Privacy Preservation of Distributed D...A Muilt-Keyword Ranked Based Search and Privacy Preservation of Distributed D...
A Muilt-Keyword Ranked Based Search and Privacy Preservation of Distributed D...
 
A Muilt-Keyword Ranked Based Search and Privacy Preservation of Distributed D...
A Muilt-Keyword Ranked Based Search and Privacy Preservation of Distributed D...A Muilt-Keyword Ranked Based Search and Privacy Preservation of Distributed D...
A Muilt-Keyword Ranked Based Search and Privacy Preservation of Distributed D...
 
Cloud migration plan1. executive summary ( 1 page)2. scope (
Cloud migration plan1. executive summary ( 1 page)2. scope (Cloud migration plan1. executive summary ( 1 page)2. scope (
Cloud migration plan1. executive summary ( 1 page)2. scope (
 
Cloud migration plan1. executive summary ( 1 page)2. scope (
Cloud migration plan1. executive summary ( 1 page)2. scope (Cloud migration plan1. executive summary ( 1 page)2. scope (
Cloud migration plan1. executive summary ( 1 page)2. scope (
 

Mais de apidays

Apidays New York 2024 - The subtle art of API rate limiting by Josh Twist, Zuplo
Apidays New York 2024 - The subtle art of API rate limiting by Josh Twist, ZuploApidays New York 2024 - The subtle art of API rate limiting by Josh Twist, Zuplo
Apidays New York 2024 - The subtle art of API rate limiting by Josh Twist, Zuploapidays
 
Apidays New York 2024 - RESTful API Patterns and Practices by Mike Amundsen, ...
Apidays New York 2024 - RESTful API Patterns and Practices by Mike Amundsen, ...Apidays New York 2024 - RESTful API Patterns and Practices by Mike Amundsen, ...
Apidays New York 2024 - RESTful API Patterns and Practices by Mike Amundsen, ...apidays
 
Apidays New York 2024 - Putting AI into API Security by Corey Ball, Moss Adams
Apidays New York 2024 - Putting AI into API Security by Corey Ball, Moss AdamsApidays New York 2024 - Putting AI into API Security by Corey Ball, Moss Adams
Apidays New York 2024 - Putting AI into API Security by Corey Ball, Moss Adamsapidays
 
Apidays New York 2024 - Prototype-first - A modern API development workflow b...
Apidays New York 2024 - Prototype-first - A modern API development workflow b...Apidays New York 2024 - Prototype-first - A modern API development workflow b...
Apidays New York 2024 - Prototype-first - A modern API development workflow b...apidays
 
Apidays New York 2024 - Post-Quantum API Security by Francois Lascelles, Broa...
Apidays New York 2024 - Post-Quantum API Security by Francois Lascelles, Broa...Apidays New York 2024 - Post-Quantum API Security by Francois Lascelles, Broa...
Apidays New York 2024 - Post-Quantum API Security by Francois Lascelles, Broa...apidays
 
Apidays New York 2024 - Increase your productivity with no-code GraphQL mocki...
Apidays New York 2024 - Increase your productivity with no-code GraphQL mocki...Apidays New York 2024 - Increase your productivity with no-code GraphQL mocki...
Apidays New York 2024 - Increase your productivity with no-code GraphQL mocki...apidays
 
Apidays New York 2024 - Driving API & EDA Success by Marcelo Caponi, Danone
Apidays New York 2024 - Driving API & EDA Success by Marcelo Caponi, DanoneApidays New York 2024 - Driving API & EDA Success by Marcelo Caponi, Danone
Apidays New York 2024 - Driving API & EDA Success by Marcelo Caponi, Danoneapidays
 
Apidays New York 2024 - Build a terrible API for people you hate by Jim Benne...
Apidays New York 2024 - Build a terrible API for people you hate by Jim Benne...Apidays New York 2024 - Build a terrible API for people you hate by Jim Benne...
Apidays New York 2024 - Build a terrible API for people you hate by Jim Benne...apidays
 
Apidays New York 2024 - API Secret Tokens Exposed by Tristan Kalos and Antoin...
Apidays New York 2024 - API Secret Tokens Exposed by Tristan Kalos and Antoin...Apidays New York 2024 - API Secret Tokens Exposed by Tristan Kalos and Antoin...
Apidays New York 2024 - API Secret Tokens Exposed by Tristan Kalos and Antoin...apidays
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobeapidays
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...apidays
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...apidays
 
Apidays New York 2024 - The secrets to Graph success, by Leah Hurwich Adler, ...
Apidays New York 2024 - The secrets to Graph success, by Leah Hurwich Adler, ...Apidays New York 2024 - The secrets to Graph success, by Leah Hurwich Adler, ...
Apidays New York 2024 - The secrets to Graph success, by Leah Hurwich Adler, ...apidays
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...apidays
 
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...apidays
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...apidays
 
Apidays New York 2024 - API Discovery - From Crawl to Run by Rob Dickinson, G...
Apidays New York 2024 - API Discovery - From Crawl to Run by Rob Dickinson, G...Apidays New York 2024 - API Discovery - From Crawl to Run by Rob Dickinson, G...
Apidays New York 2024 - API Discovery - From Crawl to Run by Rob Dickinson, G...apidays
 
Apidays Singapore 2024 - Building with the Planet in Mind by Sandeep Joshi, M...
Apidays Singapore 2024 - Building with the Planet in Mind by Sandeep Joshi, M...Apidays Singapore 2024 - Building with the Planet in Mind by Sandeep Joshi, M...
Apidays Singapore 2024 - Building with the Planet in Mind by Sandeep Joshi, M...apidays
 
Apidays Singapore 2024 - Connecting Cross Border Commerce with Payments by Gu...
Apidays Singapore 2024 - Connecting Cross Border Commerce with Payments by Gu...Apidays Singapore 2024 - Connecting Cross Border Commerce with Payments by Gu...
Apidays Singapore 2024 - Connecting Cross Border Commerce with Payments by Gu...apidays
 
Apidays Singapore 2024 - Blending AI and IoT for Smarter Health by Matthew Ch...
Apidays Singapore 2024 - Blending AI and IoT for Smarter Health by Matthew Ch...Apidays Singapore 2024 - Blending AI and IoT for Smarter Health by Matthew Ch...
Apidays Singapore 2024 - Blending AI and IoT for Smarter Health by Matthew Ch...apidays
 

Mais de apidays (20)

Apidays New York 2024 - The subtle art of API rate limiting by Josh Twist, Zuplo
Apidays New York 2024 - The subtle art of API rate limiting by Josh Twist, ZuploApidays New York 2024 - The subtle art of API rate limiting by Josh Twist, Zuplo
Apidays New York 2024 - The subtle art of API rate limiting by Josh Twist, Zuplo
 
Apidays New York 2024 - RESTful API Patterns and Practices by Mike Amundsen, ...
Apidays New York 2024 - RESTful API Patterns and Practices by Mike Amundsen, ...Apidays New York 2024 - RESTful API Patterns and Practices by Mike Amundsen, ...
Apidays New York 2024 - RESTful API Patterns and Practices by Mike Amundsen, ...
 
Apidays New York 2024 - Putting AI into API Security by Corey Ball, Moss Adams
Apidays New York 2024 - Putting AI into API Security by Corey Ball, Moss AdamsApidays New York 2024 - Putting AI into API Security by Corey Ball, Moss Adams
Apidays New York 2024 - Putting AI into API Security by Corey Ball, Moss Adams
 
Apidays New York 2024 - Prototype-first - A modern API development workflow b...
Apidays New York 2024 - Prototype-first - A modern API development workflow b...Apidays New York 2024 - Prototype-first - A modern API development workflow b...
Apidays New York 2024 - Prototype-first - A modern API development workflow b...
 
Apidays New York 2024 - Post-Quantum API Security by Francois Lascelles, Broa...
Apidays New York 2024 - Post-Quantum API Security by Francois Lascelles, Broa...Apidays New York 2024 - Post-Quantum API Security by Francois Lascelles, Broa...
Apidays New York 2024 - Post-Quantum API Security by Francois Lascelles, Broa...
 
Apidays New York 2024 - Increase your productivity with no-code GraphQL mocki...
Apidays New York 2024 - Increase your productivity with no-code GraphQL mocki...Apidays New York 2024 - Increase your productivity with no-code GraphQL mocki...
Apidays New York 2024 - Increase your productivity with no-code GraphQL mocki...
 
Apidays New York 2024 - Driving API & EDA Success by Marcelo Caponi, Danone
Apidays New York 2024 - Driving API & EDA Success by Marcelo Caponi, DanoneApidays New York 2024 - Driving API & EDA Success by Marcelo Caponi, Danone
Apidays New York 2024 - Driving API & EDA Success by Marcelo Caponi, Danone
 
Apidays New York 2024 - Build a terrible API for people you hate by Jim Benne...
Apidays New York 2024 - Build a terrible API for people you hate by Jim Benne...Apidays New York 2024 - Build a terrible API for people you hate by Jim Benne...
Apidays New York 2024 - Build a terrible API for people you hate by Jim Benne...
 
Apidays New York 2024 - API Secret Tokens Exposed by Tristan Kalos and Antoin...
Apidays New York 2024 - API Secret Tokens Exposed by Tristan Kalos and Antoin...Apidays New York 2024 - API Secret Tokens Exposed by Tristan Kalos and Antoin...
Apidays New York 2024 - API Secret Tokens Exposed by Tristan Kalos and Antoin...
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Apidays New York 2024 - The secrets to Graph success, by Leah Hurwich Adler, ...
Apidays New York 2024 - The secrets to Graph success, by Leah Hurwich Adler, ...Apidays New York 2024 - The secrets to Graph success, by Leah Hurwich Adler, ...
Apidays New York 2024 - The secrets to Graph success, by Leah Hurwich Adler, ...
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
Apidays New York 2024 - API Discovery - From Crawl to Run by Rob Dickinson, G...
Apidays New York 2024 - API Discovery - From Crawl to Run by Rob Dickinson, G...Apidays New York 2024 - API Discovery - From Crawl to Run by Rob Dickinson, G...
Apidays New York 2024 - API Discovery - From Crawl to Run by Rob Dickinson, G...
 
Apidays Singapore 2024 - Building with the Planet in Mind by Sandeep Joshi, M...
Apidays Singapore 2024 - Building with the Planet in Mind by Sandeep Joshi, M...Apidays Singapore 2024 - Building with the Planet in Mind by Sandeep Joshi, M...
Apidays Singapore 2024 - Building with the Planet in Mind by Sandeep Joshi, M...
 
Apidays Singapore 2024 - Connecting Cross Border Commerce with Payments by Gu...
Apidays Singapore 2024 - Connecting Cross Border Commerce with Payments by Gu...Apidays Singapore 2024 - Connecting Cross Border Commerce with Payments by Gu...
Apidays Singapore 2024 - Connecting Cross Border Commerce with Payments by Gu...
 
Apidays Singapore 2024 - Blending AI and IoT for Smarter Health by Matthew Ch...
Apidays Singapore 2024 - Blending AI and IoT for Smarter Health by Matthew Ch...Apidays Singapore 2024 - Blending AI and IoT for Smarter Health by Matthew Ch...
Apidays Singapore 2024 - Blending AI and IoT for Smarter Health by Matthew Ch...
 

Último

Intro in Product Management - Коротко про професію продакт менеджера
Intro in Product Management - Коротко про професію продакт менеджераIntro in Product Management - Коротко про професію продакт менеджера
Intro in Product Management - Коротко про професію продакт менеджераMark Opanasiuk
 
Structuring Teams and Portfolios for Success
Structuring Teams and Portfolios for SuccessStructuring Teams and Portfolios for Success
Structuring Teams and Portfolios for SuccessUXDXConf
 
Optimizing NoSQL Performance Through Observability
Optimizing NoSQL Performance Through ObservabilityOptimizing NoSQL Performance Through Observability
Optimizing NoSQL Performance Through ObservabilityScyllaDB
 
Free and Effective: Making Flows Publicly Accessible, Yumi Ibrahimzade
Free and Effective: Making Flows Publicly Accessible, Yumi IbrahimzadeFree and Effective: Making Flows Publicly Accessible, Yumi Ibrahimzade
Free and Effective: Making Flows Publicly Accessible, Yumi IbrahimzadeCzechDreamin
 
Buy Epson EcoTank L3210 Colour Printer Online.pdf
Buy Epson EcoTank L3210 Colour Printer Online.pdfBuy Epson EcoTank L3210 Colour Printer Online.pdf
Buy Epson EcoTank L3210 Colour Printer Online.pdfEasyPrinterHelp
 
IESVE for Early Stage Design and Planning
IESVE for Early Stage Design and PlanningIESVE for Early Stage Design and Planning
IESVE for Early Stage Design and PlanningIES VE
 
ECS 2024 Teams Premium - Pretty Secure
ECS 2024   Teams Premium - Pretty SecureECS 2024   Teams Premium - Pretty Secure
ECS 2024 Teams Premium - Pretty SecureFemke de Vroome
 
UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2DianaGray10
 
Connecting the Dots in Product Design at KAYAK
Connecting the Dots in Product Design at KAYAKConnecting the Dots in Product Design at KAYAK
Connecting the Dots in Product Design at KAYAKUXDXConf
 
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)Julian Hyde
 
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...FIDO Alliance
 
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdfSimplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdfFIDO Alliance
 
Salesforce Adoption – Metrics, Methods, and Motivation, Antone Kom
Salesforce Adoption – Metrics, Methods, and Motivation, Antone KomSalesforce Adoption – Metrics, Methods, and Motivation, Antone Kom
Salesforce Adoption – Metrics, Methods, and Motivation, Antone KomCzechDreamin
 
Top 10 Symfony Development Companies 2024
Top 10 Symfony Development Companies 2024Top 10 Symfony Development Companies 2024
Top 10 Symfony Development Companies 2024TopCSSGallery
 
What's New in Teams Calling, Meetings and Devices April 2024
What's New in Teams Calling, Meetings and Devices April 2024What's New in Teams Calling, Meetings and Devices April 2024
What's New in Teams Calling, Meetings and Devices April 2024Stephanie Beckett
 
Designing for Hardware Accessibility at Comcast
Designing for Hardware Accessibility at ComcastDesigning for Hardware Accessibility at Comcast
Designing for Hardware Accessibility at ComcastUXDXConf
 
A Business-Centric Approach to Design System Strategy
A Business-Centric Approach to Design System StrategyA Business-Centric Approach to Design System Strategy
A Business-Centric Approach to Design System StrategyUXDXConf
 
WSO2CONMay2024OpenSourceConferenceDebrief.pptx
WSO2CONMay2024OpenSourceConferenceDebrief.pptxWSO2CONMay2024OpenSourceConferenceDebrief.pptx
WSO2CONMay2024OpenSourceConferenceDebrief.pptxJennifer Lim
 
Enterprise Knowledge Graphs - Data Summit 2024
Enterprise Knowledge Graphs - Data Summit 2024Enterprise Knowledge Graphs - Data Summit 2024
Enterprise Knowledge Graphs - Data Summit 2024Enterprise Knowledge
 
Where to Learn More About FDO _ Richard at FIDO Alliance.pdf
Where to Learn More About FDO _ Richard at FIDO Alliance.pdfWhere to Learn More About FDO _ Richard at FIDO Alliance.pdf
Where to Learn More About FDO _ Richard at FIDO Alliance.pdfFIDO Alliance
 

Último (20)

Intro in Product Management - Коротко про професію продакт менеджера
Intro in Product Management - Коротко про професію продакт менеджераIntro in Product Management - Коротко про професію продакт менеджера
Intro in Product Management - Коротко про професію продакт менеджера
 
Structuring Teams and Portfolios for Success
Structuring Teams and Portfolios for SuccessStructuring Teams and Portfolios for Success
Structuring Teams and Portfolios for Success
 
Optimizing NoSQL Performance Through Observability
Optimizing NoSQL Performance Through ObservabilityOptimizing NoSQL Performance Through Observability
Optimizing NoSQL Performance Through Observability
 
Free and Effective: Making Flows Publicly Accessible, Yumi Ibrahimzade
Free and Effective: Making Flows Publicly Accessible, Yumi IbrahimzadeFree and Effective: Making Flows Publicly Accessible, Yumi Ibrahimzade
Free and Effective: Making Flows Publicly Accessible, Yumi Ibrahimzade
 
Buy Epson EcoTank L3210 Colour Printer Online.pdf
Buy Epson EcoTank L3210 Colour Printer Online.pdfBuy Epson EcoTank L3210 Colour Printer Online.pdf
Buy Epson EcoTank L3210 Colour Printer Online.pdf
 
IESVE for Early Stage Design and Planning
IESVE for Early Stage Design and PlanningIESVE for Early Stage Design and Planning
IESVE for Early Stage Design and Planning
 
ECS 2024 Teams Premium - Pretty Secure
ECS 2024   Teams Premium - Pretty SecureECS 2024   Teams Premium - Pretty Secure
ECS 2024 Teams Premium - Pretty Secure
 
UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2UiPath Test Automation using UiPath Test Suite series, part 2
UiPath Test Automation using UiPath Test Suite series, part 2
 
Connecting the Dots in Product Design at KAYAK
Connecting the Dots in Product Design at KAYAKConnecting the Dots in Product Design at KAYAK
Connecting the Dots in Product Design at KAYAK
 
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)
Measures in SQL (a talk at SF Distributed Systems meetup, 2024-05-22)
 
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
Choosing the Right FDO Deployment Model for Your Application _ Geoffrey at In...
 
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdfSimplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
Simplified FDO Manufacturing Flow with TPMs _ Liam at Infineon.pdf
 
Salesforce Adoption – Metrics, Methods, and Motivation, Antone Kom
Salesforce Adoption – Metrics, Methods, and Motivation, Antone KomSalesforce Adoption – Metrics, Methods, and Motivation, Antone Kom
Salesforce Adoption – Metrics, Methods, and Motivation, Antone Kom
 
Top 10 Symfony Development Companies 2024
Top 10 Symfony Development Companies 2024Top 10 Symfony Development Companies 2024
Top 10 Symfony Development Companies 2024
 
What's New in Teams Calling, Meetings and Devices April 2024
What's New in Teams Calling, Meetings and Devices April 2024What's New in Teams Calling, Meetings and Devices April 2024
What's New in Teams Calling, Meetings and Devices April 2024
 
Designing for Hardware Accessibility at Comcast
Designing for Hardware Accessibility at ComcastDesigning for Hardware Accessibility at Comcast
Designing for Hardware Accessibility at Comcast
 
A Business-Centric Approach to Design System Strategy
A Business-Centric Approach to Design System StrategyA Business-Centric Approach to Design System Strategy
A Business-Centric Approach to Design System Strategy
 
WSO2CONMay2024OpenSourceConferenceDebrief.pptx
WSO2CONMay2024OpenSourceConferenceDebrief.pptxWSO2CONMay2024OpenSourceConferenceDebrief.pptx
WSO2CONMay2024OpenSourceConferenceDebrief.pptx
 
Enterprise Knowledge Graphs - Data Summit 2024
Enterprise Knowledge Graphs - Data Summit 2024Enterprise Knowledge Graphs - Data Summit 2024
Enterprise Knowledge Graphs - Data Summit 2024
 
Where to Learn More About FDO _ Richard at FIDO Alliance.pdf
Where to Learn More About FDO _ Richard at FIDO Alliance.pdfWhere to Learn More About FDO _ Richard at FIDO Alliance.pdf
Where to Learn More About FDO _ Richard at FIDO Alliance.pdf
 

Apidays Singapore 2024 - Privacy Enhancing Technologies for AI by Mark Choo, Federated Learning - AI Singapore

  • 1. © 2024 AI Singapore Privacy Enhancing Technologies for AI Mark Choo 17 April 2024
  • 2.
  • 3. © 2024 AI Singapore The Future of Federated Learning Is there a case for Federated Learning(FL)? Since 2016, there are more than 3,900 papers on FL being published to arXiv alone. In recent years, there is a growing number of investments made into FL by the big tech companies. In March 2023, OECD published a paper on Emerging Privacy Enhancing Technologies(PET) and recognize FL as 1 of the 4 PETs categories. This sets the stage for FL to be adopted for data privacy protection as part of Privacy Design. https://www.oecd.org/publications/emerging-privacy- enhancing-technologies-bf121be4-en.htm
  • 4. © 2024 AI Singapore How federated learning works? 1. A group of parties (with local data) come together and form a network, with the common goal to train a model together. Party A Data Party B Data Party C Data
  • 5. © 2024 AI Singapore How federated learning works? 2. The Trusted Third Party (TTP) acts as the coordinator (it does not contribute data). It sends this model to all the other participating parties. This model would serve as a baseline for each individual party to start training with only local data. Party A Data Party B Data Party C Data Trusted Third Party Model
  • 6. © 2024 AI Singapore How federated learning works? 3. Each participating party will start to train the given model with its own local data. Party A Data Party B Data Party C Data Trusted Third Party Model Model Model Model W
  • 7. © 2024 AI Singapore How federated learning works? 3. Periodically, all parties send their learning (weights, gradients, losses, etc.) to the TTP. NO local data is ever exposed. Party A Data Party B Data Party C Data Trusted Third Party Model Model Model Model W
  • 8. © 2024 AI Singapore How federated learning works? 4. The TTP then aggregates the new learnings from the parties and continues to improve the shared model. Party A Data Party B Data Party C Data Trusted Third Party Model Model Model Model W
  • 9. © 2024 AI Singapore How federated learning works? 5. The new shared model is again sent back to the participating parties and the same cycle repeats again and again. With each iteration, the shared model maintained by the TTP gets better. Party A Data Party B Data Party C Data Trusted Third Party Model Model Model Model No raw data is received
  • 10. © 2024 AI Singapore Operational Impact of Data Collaboration What is the typical organization structure during Data Centralization? Raw Data Raw Data Raw Data Raw Data Data Processor Data Controller Organization 1 Data Processor Data Controller Organization 2 Third Party Organization Consolidator Storage
  • 11. © 2024 AI Singapore Operational Impact of Data Collaboration Structure 1: Organization is both the Data Controller and Data Processor Raw Data Raw Data Data Processor Data Controller Organization 1 Consolidator Storage Organization 1 controls the full workflow Organization 1 of the federated grid is ultimately bounded by legalities regarding raw data since users’ personal data is • Processed • Stored • Organised • Collected • Disseminated Intra-organizational workflow • Regulations are between departments • Relatively easier/feasible to get access since contracts/request workflows/audits are all consistent within the organisation Data is often immobile due to data lakes
  • 12. © 2024 AI Singapore Operational Impact of Data Collaboration Structure 2: Organization is the Data Controller and Third Party is the Data Processor Raw Data Raw Data Data Processor Data Controller Organization 2 Third Party Organization Consolidator Storage Inter-Organization Efforts Third Party processes the raw data when it receives operations from orchestrator, and is bounded by legalities regarding raw data since users’ personal data is • Processed • Stored • Organised Organization 2 controls the ingestion and usage of the raw data and hence is bounded by legalities regarding raw data since users’ personal data is • Collected • Stored • Organised • Disseminated
  • 13. © 2024 AI Singapore A Different Structure for Data Collaboration Federated Grid to Truly Retain Control of Private and Proprietary Data Raw Data Raw Data Federated Node Data Controller Organization 1 Federated Node Data Controller Organization 2 Third Party Organization Orchestrator Analytics | Mathematical Weights Analytics | Mathematical Weights Federated Grid
  • 14. © 2024 AI Singapore Federated Learning Beyond Privacy What other problems can Federated Learning solve? Data Immobility ● Volume of Data can cause the duplication and transfer of data for centralized model training to be inefficient and expensive. ○ For e.g., Medical Images can be very large even at individual level. ○ For e.g., Financial Transaction Data where the business nature is data hungry. Collaborative AI ● Veracity of Data can be improved because a party’s data may not contain the whole picture, but multiple party’s data can potentially improve the quality of the data ○ For e.g., Multiple banks coming together to build a global fraud detection model. ● Value & Variety of Data can be exploited more. ○ For e.g., Supermarket and Hospital coming together to build a model to identify someone at risk of getting diabetes. Images generated with Microsoft Co-Pilot
  • 15. © 2024 AI Singapore Unlock Data with Federated Learning How can companies collaborate with their datasets? Sample ID Sample ID Features Features Overlapped Features Set (red box) Labels Dataset from A Dataset from B Labels Sample ID Sample ID Features Features Overlapped Sample Set (redbox) Labels Dataset from A Dataset from B Vertical Federated Learning Labels Horizontal Federated Learning ● A and B are from different industry and the dataset use case is likely different. ● There is an overlap of Sample set (row-wise). ● Vertical FL allows training of a global model with a larger amount of data features using the overlapped sample set. ● A and B are likely in the same industry and the dataset use case is the same with overlapping data features. ● This allow horizontal FL to train a global model with the enlarged overlapped features set. (red box) ● In other words, this means training a larger number of samples with the overlapped data features.
  • 16. © 2024 AI Singapore Centralized vs Federated Collaboration Cost Analysis of Centralized Collaborative AI vs Federated Learning Collaboration During training collaboration between different parties, the cost of centralization data can get hefty due to the data transfer and duplication of storage. * Data are taken from commercial cloud provider’s public pricing calculator * Data transfer is within the same cloud provider and between Asia region
  • 17. © 2024 AI Singapore Centralized vs Federated Collaboration Cost Analysis of Centralized Collaborative AI vs Federated Learning Collaboration 16 GB 161 GB 800 GB Since the collaborator’s cost is linear, the cost of central collaboration is approximately 5 times more than if the collaborator trains on its own. (No data duplication and no data transfer) Adopting Federated Learning as a collaboration method reduces the cost of collaboration as the dataset size scales.
  • 18. © 2024 AI Singapore Federated Learning for Public Good There is a lot more to learn if we can come together Individual organizations can only solve public good problem with their own data. But with data collaboration, we are increasing the solution space and benefit. In the example, each organization has 100 PB of data and through collaboration each organization now has 300 PB of data for learning. The total benefit will be 900 PB of data for public good.
  • 19. © 2024 AI Singapore Federated Learning for Public Good There is a lot more to learn if we can come together There is a scaling effect with the number of participants coming together to share knowledge. The more data we share, the more good we can potentially do.
  • 20. © 2024 AI Singapore AISG 100E Federated Learning Projects Examples of Federated Learning Use Case Federated Learning for ICU in-hospital mortality prediction https://link.springer.com/chapter/10.1 007/978-3-030-63076-8_18 A large multi-centre critical care database made available by Philips Healthcare in partnership with the MIT Laboratory for Computational Physiology were used. Data is anonymised and cleansed. Three hospitals with the most number of ICU stays, and most complete data were kept. A mortality prediction model was built for the research paper. Federated Predictive Maintenance for Telemetry Log Data A Global Data Infrastructure Service Provider wanted to improve the availability of services and minimize disruption for their customers by predicting when maintenance are required. However, the telemetry log data are housed at customer sites and centralizing the data are expensive and faces regulatory hurdles on data residency. The FL team implemented a Federated Learning solution that allows model customization. Federated Image Segmentation on Large OCT Scans A Global Pharmaceutical Company faces data privacy hurdles and high cost of data centralization for research. Medical images are highly sensitive and can be very large in size for even centralized ML training. The team customize & optimize Synergos with new engineering features that not only orchestrate image segmentation in a federated setting, but also to handle large medical data.
  • 21. © 2024 AI Singapore Thank you www.aisingapore.org