SlideShare a Scribd company logo
1 of 27
Download to read offline
Proposing an Interactive Audit
Pipeline for Visual Privacy
Research
Jasmine DeHart, Chenguang Xu, Lisa Egede, Christan Grant
OUDATALAB.com
2021 IEEE International Conference on Big Data (BigData)
December 15 – 18, 2021
Traditional machine learning pipelines do not consider fairness, privacy,
and ownership issues as they arise.
We recommend frameworks to use for designing new ML pipelines.
In the following slides, we present a scenario that will describe the main
points of the paper.
The Boss Engineer #1 Engineer #2
🪖
You’re now the lead for our
machine learning team.
And, I have this great idea…
You’ve been doing a
great job!
Thanks, Boss!
Let’s build a People
Counter for the downtown
Smart City initiative.
Sounds innovative. I will
put together our
traditional machine
learning pipeline!
There are so many parts
and I have to build this
pipeline from scratch...
I’ll need to design three ML
pipeline phases:
1. Data Preparation Phase;
2. Modeling Phase;
3. Deployment Phase.
Phase 1: Data Preparation
I’ll start with the Data
Preparation Phase.
Phase 2: Modeling
This Modeling Phase
might take a while.
Phase 3: Deployment
This is looking good!
Here is the
complete pipeline
for camera-based
people counter!
Phase 3: Deployment
Phase 1: Data Preparation Phase 2: Modeling
This looks great. It
follows our
traditional pipeline
standards!
We can sell
this model
and data to
companies!
Wait a minute! There are
some additional things
we need to consider.
Historical bias Algorithmic bias Software Discrimination
See paper for more details…
Multiparty Conflict Image Removal Request Obtaining Content
Consent
Human-over-the-loop
• Regular updates help to avoid
and minimize costly errors
• Allows humans to step in pro re
nata to perform corrections or
updates
• Resolve biases that may be
imposed from humans or the
model during learning
Interactive Audit Strategies
Fairness Forensic Auditing System (FASt)
• Inspect a dataset or a model via
techniques and tools for bias
• FASt has three tasks: bias
detection, bias interpretation,
and bias mitigation.
Visual Privacy Auditor (ViP)
• Inspect a dataset or a model via
techniques and tools for privacy
concerns
• Visual privacy mitigation strategies
built into the ViP Auditor.
See paper for more details…
Here’s our updated
pipeline.
Human-over-the-loop
feedback is integrated
with the Audit
Strategies.
Conclusion
• We identify portions of the machine learning pipeline that contain visual
privacy and fairness issues.
• We walkthrough the need for responsible auditing systems to bring
accountability into the ML pipeline.
• We propose using human-over-the-loop strategies for auditing fairness and
privacy issues.
Acknowledgements
• Department of Defense SMART Scholarship
• National Science Foundation Grant # 1952181
• Photo Actors: Makya Stell (The Boss)
Jessica Reese & A’Kile Stone (Engineer 1 & 2)
Backup/Old slides
Intro/Motivate
• Definitions?
• Scenario? Could use reference throughout the presentation
High-level pipeline
• Quick overview of the ml pipeline setup
Issues Pipeline
• Add a issue or two at each spot
• Describe the issues
• Point to the paper
Solution Pipeline
• Discuss those two and how they solve the problem
• FASt
• ViP
Conclude/Future Work
Proposing an Interactive Audit Pipeline for Visual Privacy Research
Proposing an Interactive Audit Pipeline for Visual Privacy Research
Proposing an Interactive Audit Pipeline for Visual Privacy Research
Proposing an Interactive Audit Pipeline for Visual Privacy Research

More Related Content

Similar to Proposing an Interactive Audit Pipeline for Visual Privacy Research

Human in the loop: Bayesian Rules Enabling Explainable AI
Human in the loop: Bayesian Rules Enabling Explainable AIHuman in the loop: Bayesian Rules Enabling Explainable AI
Human in the loop: Bayesian Rules Enabling Explainable AIPramit Choudhary
 
Running head NETWORK DIAGRAM AND WORKFLOW1NETWORK DIAGRAM AN.docx
Running head NETWORK DIAGRAM AND WORKFLOW1NETWORK DIAGRAM AN.docxRunning head NETWORK DIAGRAM AND WORKFLOW1NETWORK DIAGRAM AN.docx
Running head NETWORK DIAGRAM AND WORKFLOW1NETWORK DIAGRAM AN.docxjeanettehully
 
Machine learning and big data
Machine learning and big dataMachine learning and big data
Machine learning and big dataPoo Kuan Hoong
 
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNINGHANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNINGIRJET Journal
 
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNINGHANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNINGIRJET Journal
 
Machine Learning & IT Service Intelligence for the Enterprise: The Future is ...
Machine Learning & IT Service Intelligence for the Enterprise: The Future is ...Machine Learning & IT Service Intelligence for the Enterprise: The Future is ...
Machine Learning & IT Service Intelligence for the Enterprise: The Future is ...Precisely
 
AI In Actuarial Science
AI In Actuarial ScienceAI In Actuarial Science
AI In Actuarial ScienceAudrey Britton
 
L1 Introduction DS.pptx
L1 Introduction DS.pptxL1 Introduction DS.pptx
L1 Introduction DS.pptxShambhavi Vats
 
If You Are Not Embedding Analytics Into Your Day To Day Processes, You Are Do...
If You Are Not Embedding Analytics Into Your Day To Day Processes, You Are Do...If You Are Not Embedding Analytics Into Your Day To Day Processes, You Are Do...
If You Are Not Embedding Analytics Into Your Day To Day Processes, You Are Do...Dell World
 
Loan Prediction System Using Machine Learning.pptx
Loan Prediction System Using Machine Learning.pptxLoan Prediction System Using Machine Learning.pptx
Loan Prediction System Using Machine Learning.pptxBhoirRitesh19ET5008
 
IRJET- Fault Detection and Prediction of Failure using Vibration Analysis
IRJET-	 Fault Detection and Prediction of Failure using Vibration AnalysisIRJET-	 Fault Detection and Prediction of Failure using Vibration Analysis
IRJET- Fault Detection and Prediction of Failure using Vibration AnalysisIRJET Journal
 
التنقيب في البيانات - Data Mining
التنقيب في البيانات -  Data Miningالتنقيب في البيانات -  Data Mining
التنقيب في البيانات - Data Miningnabil_alsharafi
 
Model governance in the age of data science & AI
Model governance in the age of data science & AIModel governance in the age of data science & AI
Model governance in the age of data science & AIQuantUniversity
 
Advanced Project Data Analytics for Improved Project Delivery
Advanced Project Data Analytics for Improved Project DeliveryAdvanced Project Data Analytics for Improved Project Delivery
Advanced Project Data Analytics for Improved Project DeliveryMark Constable
 
Pydata Chicago - work hard once
Pydata Chicago - work hard oncePydata Chicago - work hard once
Pydata Chicago - work hard onceJi Dong
 
IRJET - Real Time Facial Analysis using Tensorflowand OpenCV
IRJET -  	  Real Time Facial Analysis using Tensorflowand OpenCVIRJET -  	  Real Time Facial Analysis using Tensorflowand OpenCV
IRJET - Real Time Facial Analysis using Tensorflowand OpenCVIRJET Journal
 
Intelligently Automating Machine Learning, Artificial Intelligence, and Data ...
Intelligently Automating Machine Learning, Artificial Intelligence, and Data ...Intelligently Automating Machine Learning, Artificial Intelligence, and Data ...
Intelligently Automating Machine Learning, Artificial Intelligence, and Data ...Ali Alkan
 
“Responsible AI: Tools and Frameworks for Developing AI Solutions,” a Present...
“Responsible AI: Tools and Frameworks for Developing AI Solutions,” a Present...“Responsible AI: Tools and Frameworks for Developing AI Solutions,” a Present...
“Responsible AI: Tools and Frameworks for Developing AI Solutions,” a Present...Edge AI and Vision Alliance
 

Similar to Proposing an Interactive Audit Pipeline for Visual Privacy Research (20)

Human in the loop: Bayesian Rules Enabling Explainable AI
Human in the loop: Bayesian Rules Enabling Explainable AIHuman in the loop: Bayesian Rules Enabling Explainable AI
Human in the loop: Bayesian Rules Enabling Explainable AI
 
Running head NETWORK DIAGRAM AND WORKFLOW1NETWORK DIAGRAM AN.docx
Running head NETWORK DIAGRAM AND WORKFLOW1NETWORK DIAGRAM AN.docxRunning head NETWORK DIAGRAM AND WORKFLOW1NETWORK DIAGRAM AN.docx
Running head NETWORK DIAGRAM AND WORKFLOW1NETWORK DIAGRAM AN.docx
 
Machine learning and big data
Machine learning and big dataMachine learning and big data
Machine learning and big data
 
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNINGHANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
 
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNINGHANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
HANDWRITTEN DIGIT RECOGNITION USING MACHINE LEARNING
 
Machine Learning & IT Service Intelligence for the Enterprise: The Future is ...
Machine Learning & IT Service Intelligence for the Enterprise: The Future is ...Machine Learning & IT Service Intelligence for the Enterprise: The Future is ...
Machine Learning & IT Service Intelligence for the Enterprise: The Future is ...
 
AI In Actuarial Science
AI In Actuarial ScienceAI In Actuarial Science
AI In Actuarial Science
 
L1 Introduction DS.pptx
L1 Introduction DS.pptxL1 Introduction DS.pptx
L1 Introduction DS.pptx
 
If You Are Not Embedding Analytics Into Your Day To Day Processes, You Are Do...
If You Are Not Embedding Analytics Into Your Day To Day Processes, You Are Do...If You Are Not Embedding Analytics Into Your Day To Day Processes, You Are Do...
If You Are Not Embedding Analytics Into Your Day To Day Processes, You Are Do...
 
Loan Prediction System Using Machine Learning.pptx
Loan Prediction System Using Machine Learning.pptxLoan Prediction System Using Machine Learning.pptx
Loan Prediction System Using Machine Learning.pptx
 
Machine learning in Banks
Machine learning in BanksMachine learning in Banks
Machine learning in Banks
 
IRJET- Fault Detection and Prediction of Failure using Vibration Analysis
IRJET-	 Fault Detection and Prediction of Failure using Vibration AnalysisIRJET-	 Fault Detection and Prediction of Failure using Vibration Analysis
IRJET- Fault Detection and Prediction of Failure using Vibration Analysis
 
التنقيب في البيانات - Data Mining
التنقيب في البيانات -  Data Miningالتنقيب في البيانات -  Data Mining
التنقيب في البيانات - Data Mining
 
Model governance in the age of data science & AI
Model governance in the age of data science & AIModel governance in the age of data science & AI
Model governance in the age of data science & AI
 
Advanced Project Data Analytics for Improved Project Delivery
Advanced Project Data Analytics for Improved Project DeliveryAdvanced Project Data Analytics for Improved Project Delivery
Advanced Project Data Analytics for Improved Project Delivery
 
ODSC APAC 2022 - Explainable AI
ODSC APAC 2022 - Explainable AIODSC APAC 2022 - Explainable AI
ODSC APAC 2022 - Explainable AI
 
Pydata Chicago - work hard once
Pydata Chicago - work hard oncePydata Chicago - work hard once
Pydata Chicago - work hard once
 
IRJET - Real Time Facial Analysis using Tensorflowand OpenCV
IRJET -  	  Real Time Facial Analysis using Tensorflowand OpenCVIRJET -  	  Real Time Facial Analysis using Tensorflowand OpenCV
IRJET - Real Time Facial Analysis using Tensorflowand OpenCV
 
Intelligently Automating Machine Learning, Artificial Intelligence, and Data ...
Intelligently Automating Machine Learning, Artificial Intelligence, and Data ...Intelligently Automating Machine Learning, Artificial Intelligence, and Data ...
Intelligently Automating Machine Learning, Artificial Intelligence, and Data ...
 
“Responsible AI: Tools and Frameworks for Developing AI Solutions,” a Present...
“Responsible AI: Tools and Frameworks for Developing AI Solutions,” a Present...“Responsible AI: Tools and Frameworks for Developing AI Solutions,” a Present...
“Responsible AI: Tools and Frameworks for Developing AI Solutions,” a Present...
 

Recently uploaded

CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfCCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfAsst.prof M.Gokilavani
 
Introduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptxIntroduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptxk795866
 
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdfCCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdfAsst.prof M.Gokilavani
 
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerStudy on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerAnamika Sarkar
 
Work Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvWork Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvLewisJB
 
Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024hassan khalil
 
Concrete Mix Design - IS 10262-2019 - .pptx
Concrete Mix Design - IS 10262-2019 - .pptxConcrete Mix Design - IS 10262-2019 - .pptx
Concrete Mix Design - IS 10262-2019 - .pptxKartikeyaDwivedi3
 
complete construction, environmental and economics information of biomass com...
complete construction, environmental and economics information of biomass com...complete construction, environmental and economics information of biomass com...
complete construction, environmental and economics information of biomass com...asadnawaz62
 
An introduction to Semiconductor and its types.pptx
An introduction to Semiconductor and its types.pptxAn introduction to Semiconductor and its types.pptx
An introduction to Semiconductor and its types.pptxPurva Nikam
 
Past, Present and Future of Generative AI
Past, Present and Future of Generative AIPast, Present and Future of Generative AI
Past, Present and Future of Generative AIabhishek36461
 
Application of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptxApplication of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptx959SahilShah
 
Arduino_CSE ece ppt for working and principal of arduino.ppt
Arduino_CSE ece ppt for working and principal of arduino.pptArduino_CSE ece ppt for working and principal of arduino.ppt
Arduino_CSE ece ppt for working and principal of arduino.pptSAURABHKUMAR892774
 
What are the advantages and disadvantages of membrane structures.pptx
What are the advantages and disadvantages of membrane structures.pptxWhat are the advantages and disadvantages of membrane structures.pptx
What are the advantages and disadvantages of membrane structures.pptxwendy cai
 
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)Dr SOUNDIRARAJ N
 
Comparative Analysis of Text Summarization Techniques
Comparative Analysis of Text Summarization TechniquesComparative Analysis of Text Summarization Techniques
Comparative Analysis of Text Summarization Techniquesugginaramesh
 
Correctly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleCorrectly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleAlluxio, Inc.
 
Call Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile serviceCall Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile servicerehmti665
 
8251 universal synchronous asynchronous receiver transmitter
8251 universal synchronous asynchronous receiver transmitter8251 universal synchronous asynchronous receiver transmitter
8251 universal synchronous asynchronous receiver transmitterShivangiSharma879191
 

Recently uploaded (20)

CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfCCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
 
Introduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptxIntroduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptx
 
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdfCCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
 
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerStudy on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
 
young call girls in Green Park🔝 9953056974 🔝 escort Service
young call girls in Green Park🔝 9953056974 🔝 escort Serviceyoung call girls in Green Park🔝 9953056974 🔝 escort Service
young call girls in Green Park🔝 9953056974 🔝 escort Service
 
Work Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvWork Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvv
 
Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024
 
Concrete Mix Design - IS 10262-2019 - .pptx
Concrete Mix Design - IS 10262-2019 - .pptxConcrete Mix Design - IS 10262-2019 - .pptx
Concrete Mix Design - IS 10262-2019 - .pptx
 
complete construction, environmental and economics information of biomass com...
complete construction, environmental and economics information of biomass com...complete construction, environmental and economics information of biomass com...
complete construction, environmental and economics information of biomass com...
 
An introduction to Semiconductor and its types.pptx
An introduction to Semiconductor and its types.pptxAn introduction to Semiconductor and its types.pptx
An introduction to Semiconductor and its types.pptx
 
Past, Present and Future of Generative AI
Past, Present and Future of Generative AIPast, Present and Future of Generative AI
Past, Present and Future of Generative AI
 
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCRCall Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
 
Application of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptxApplication of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptx
 
Arduino_CSE ece ppt for working and principal of arduino.ppt
Arduino_CSE ece ppt for working and principal of arduino.pptArduino_CSE ece ppt for working and principal of arduino.ppt
Arduino_CSE ece ppt for working and principal of arduino.ppt
 
What are the advantages and disadvantages of membrane structures.pptx
What are the advantages and disadvantages of membrane structures.pptxWhat are the advantages and disadvantages of membrane structures.pptx
What are the advantages and disadvantages of membrane structures.pptx
 
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)
UNIT III ANALOG ELECTRONICS (BASIC ELECTRONICS)
 
Comparative Analysis of Text Summarization Techniques
Comparative Analysis of Text Summarization TechniquesComparative Analysis of Text Summarization Techniques
Comparative Analysis of Text Summarization Techniques
 
Correctly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleCorrectly Loading Incremental Data at Scale
Correctly Loading Incremental Data at Scale
 
Call Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile serviceCall Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile service
 
8251 universal synchronous asynchronous receiver transmitter
8251 universal synchronous asynchronous receiver transmitter8251 universal synchronous asynchronous receiver transmitter
8251 universal synchronous asynchronous receiver transmitter
 

Proposing an Interactive Audit Pipeline for Visual Privacy Research

  • 1. Proposing an Interactive Audit Pipeline for Visual Privacy Research Jasmine DeHart, Chenguang Xu, Lisa Egede, Christan Grant OUDATALAB.com 2021 IEEE International Conference on Big Data (BigData) December 15 – 18, 2021
  • 2. Traditional machine learning pipelines do not consider fairness, privacy, and ownership issues as they arise. We recommend frameworks to use for designing new ML pipelines. In the following slides, we present a scenario that will describe the main points of the paper. The Boss Engineer #1 Engineer #2
  • 3. 🪖 You’re now the lead for our machine learning team. And, I have this great idea… You’ve been doing a great job! Thanks, Boss!
  • 4. Let’s build a People Counter for the downtown Smart City initiative. Sounds innovative. I will put together our traditional machine learning pipeline!
  • 5. There are so many parts and I have to build this pipeline from scratch... I’ll need to design three ML pipeline phases: 1. Data Preparation Phase; 2. Modeling Phase; 3. Deployment Phase.
  • 6. Phase 1: Data Preparation I’ll start with the Data Preparation Phase.
  • 7. Phase 2: Modeling This Modeling Phase might take a while.
  • 8. Phase 3: Deployment This is looking good!
  • 9. Here is the complete pipeline for camera-based people counter! Phase 3: Deployment Phase 1: Data Preparation Phase 2: Modeling
  • 10. This looks great. It follows our traditional pipeline standards!
  • 11. We can sell this model and data to companies! Wait a minute! There are some additional things we need to consider.
  • 12. Historical bias Algorithmic bias Software Discrimination See paper for more details… Multiparty Conflict Image Removal Request Obtaining Content Consent
  • 13. Human-over-the-loop • Regular updates help to avoid and minimize costly errors • Allows humans to step in pro re nata to perform corrections or updates • Resolve biases that may be imposed from humans or the model during learning
  • 14. Interactive Audit Strategies Fairness Forensic Auditing System (FASt) • Inspect a dataset or a model via techniques and tools for bias • FASt has three tasks: bias detection, bias interpretation, and bias mitigation. Visual Privacy Auditor (ViP) • Inspect a dataset or a model via techniques and tools for privacy concerns • Visual privacy mitigation strategies built into the ViP Auditor. See paper for more details…
  • 15. Here’s our updated pipeline. Human-over-the-loop feedback is integrated with the Audit Strategies.
  • 16. Conclusion • We identify portions of the machine learning pipeline that contain visual privacy and fairness issues. • We walkthrough the need for responsible auditing systems to bring accountability into the ML pipeline. • We propose using human-over-the-loop strategies for auditing fairness and privacy issues.
  • 17. Acknowledgements • Department of Defense SMART Scholarship • National Science Foundation Grant # 1952181 • Photo Actors: Makya Stell (The Boss) Jessica Reese & A’Kile Stone (Engineer 1 & 2)
  • 19. Intro/Motivate • Definitions? • Scenario? Could use reference throughout the presentation
  • 20. High-level pipeline • Quick overview of the ml pipeline setup
  • 21. Issues Pipeline • Add a issue or two at each spot • Describe the issues • Point to the paper
  • 22. Solution Pipeline • Discuss those two and how they solve the problem • FASt • ViP