SlideShare a Scribd company logo
1 of 25
Download to read offline
Kevin Smeyers
Evolutionary Architect
kevin.smeyers@tothepoint.company
@ksmeyers
1
AI – Artificial Intelligence
The Dangers
M2Q – 01 April 2019
• Adversarial attacks
• Tricking Models
• Reverse engineering of models (leaking information)
• Poisoned data
• Bias in data
• Building the right model with the wrong conclusions
• Ethics
• Privacy? Using AI for good!
• Deepfake
• GPT2
• Security in general
https://pralab.diee.unica.it/sites/default/files/biggio18-pr.pdf
• High-Level Representation Guided Denoising
• Adversarial training
• Pixel Deflection
• ….
• Toolboxes
• Advertorch – robustness tester
• https://github.com/tensorflow/cleverhans
• ….
Read the following book….
Read the following book….
The square peg bias
This is where you just choose the wrong data set because it's what you have.
For example: You want model sportswear purchases for your online clothing store, but you only have data on what
people have been buying at brick-and-mortar shops.
Sampling bias
You choose your data to represent an environment.
Generally, you choose a subset of data that is representative and sufficiently large, but you have to watch out for the
human biases in picking that data; it can be as innocent as forgetting to include nighttime data in a training set
for facial recognition.
http://beauty.ai
https://www.techrepublic.com/article/top-10-ai-failures-of-2016/
Bias-variance trade-off
You may cause bias by overcorrecting for variance. If your model is too sensitive to variance, small fluctuations could
cause it to model random noise. Too much bias to correct this could miss complexity.
Nearest neighbor prediction regions.
Lighter colors indicate less certainty about predictions. You can adjust the value of k.
Value of k has direct impact on bias-variance trade-off
Bias-variance trade-off
You may cause bias by overcorrecting for variance. If your model is too sensitive to variance, small fluctuations could
cause it to model random noise. Too much bias to correct this could miss complexity.
Nearest neighbor prediction regions.
Lighter colors indicate less certainty about predictions. You can adjust the value of k.
Value of k has direct impact on bias-variance trade-off
Bias-variance trade-off
You may cause bias by overcorrecting for variance. If your model is too sensitive to variance, small fluctuations could
cause it to model random noise. Too much bias to correct this could miss complexity.
Nearest neighbor prediction regions.
Lighter colors indicate less certainty about predictions. You can adjust the value of k.
Value of k has direct impact on bias-variance trade-off
Measurement bias
This is when the device you use to collect the data has bias built in, like say a scale that incorrectly overestimates
weight;
so the data is sound, and no statistical correction would catch it.
Having multiple measuring devices can help prevent this.
Stereotype bias
You're training a machine learning algorithm to recognize people at work, so you give it lots of images of male
doctors and women teachers.
This might even be mathematically sound, since the stereotype is social and might exist in the data without you even
getting involved. But if you want a stronger ML, you'll need to correct for that social stereotype.
https://arxiv.org/pdf/1607.06520.pdf
man − woman ≈ computer programmer − homemaker.
• Have objective acceptance criteria. Know the amount of error you and your users are
willing to accept
• Test with new data.
• Don’t count on all results being accurate.
• Understand the architecture of the network as a part of the testing process
• Communicate the level of confidence you have in the results to management and users.
• Model performance
• Metamorphic testing
• C. Murphy, G. E. Kaiser, L. Hu, and L. Wu, “Properties of Machine Learning Applications for Use in
Metamorphic Testing,” in SEKE, 2008, vol. 8, pp. 867–872
• Driverless vehicle
https://www.researchgate.net/publication/331289445_Metamorphic_testing_of_driverless_cars
• Dual coding
• Coverage guided fuzzing
• TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing
• Comparison with simplified, linear models
• Testing with different data slices
Alan Turing
“if a machine is expected to be infallible, it cannot also be intelligent”
Gary Kasparov
(@AMLD2019)
We aren’t be replaced,
we are begin promoted
Dr. Viviene Ming (@SuperNova)
Good technology shouldn’t
substitute what we do,
it should make us better at doing
it.
Example Sexy Face
Zeynep Tufekci (@AMLD2019)
#ML and #AI surfacing and
exploiting #biases that we are not
even aware of — because we had
no way to identify them at scale
Asking them for open ending
questions….
http://moralmachine.mit.edu
https://tothepoint.group/news/the-dangers-of-image-recognition/
Attacking image recognition models -> infamous twin tests:
THANK YOU
Questions?
Shoot!
@ksmeyers

More Related Content

Similar to The Dangers of Machine Learning

Generative Adversarial Network (GAN)
Generative Adversarial Network (GAN)Generative Adversarial Network (GAN)
Generative Adversarial Network (GAN)Prakhar Rastogi
 
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018Sri Ambati
 
Machine Learning Foundations for Professional Managers
Machine Learning Foundations for Professional ManagersMachine Learning Foundations for Professional Managers
Machine Learning Foundations for Professional ManagersAlbert Y. C. Chen
 
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...Edge AI and Vision Alliance
 
Big Data Spain 2018: How to build Weighted XGBoost ML model for Imbalance dat...
Big Data Spain 2018: How to build Weighted XGBoost ML model for Imbalance dat...Big Data Spain 2018: How to build Weighted XGBoost ML model for Imbalance dat...
Big Data Spain 2018: How to build Weighted XGBoost ML model for Imbalance dat...Alok Singh
 
Hacking Predictive Modeling - RoadSec 2018
Hacking Predictive Modeling - RoadSec 2018Hacking Predictive Modeling - RoadSec 2018
Hacking Predictive Modeling - RoadSec 2018HJ van Veen
 
Model evaluation in the land of deep learning
Model evaluation in the land of deep learningModel evaluation in the land of deep learning
Model evaluation in the land of deep learningPramit Choudhary
 
Build, train, and deploy ML models with Amazon SageMaker - AIM302 - New York ...
Build, train, and deploy ML models with Amazon SageMaker - AIM302 - New York ...Build, train, and deploy ML models with Amazon SageMaker - AIM302 - New York ...
Build, train, and deploy ML models with Amazon SageMaker - AIM302 - New York ...Amazon Web Services
 
Engineering Machine Learning Data Pipelines Series: Big Data Quality - Cleans...
Engineering Machine Learning Data Pipelines Series: Big Data Quality - Cleans...Engineering Machine Learning Data Pipelines Series: Big Data Quality - Cleans...
Engineering Machine Learning Data Pipelines Series: Big Data Quality - Cleans...Precisely
 
The importance of model fairness and interpretability in AI systems
The importance of model fairness and interpretability in AI systemsThe importance of model fairness and interpretability in AI systems
The importance of model fairness and interpretability in AI systemsFrancesca Lazzeri, PhD
 
Choosing a Machine Learning technique to solve your need
Choosing a Machine Learning technique to solve your needChoosing a Machine Learning technique to solve your need
Choosing a Machine Learning technique to solve your needGibDevs
 
High time to add machine learning to your information security stack
High time to add machine learning to your information security stackHigh time to add machine learning to your information security stack
High time to add machine learning to your information security stackMinhaz A V
 
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...Egyptian Engineers Association
 
Explainability and bias in AI
Explainability and bias in AIExplainability and bias in AI
Explainability and bias in AIBill Liu
 
Spark + AI Summit - The Importance of Model Fairness and Interpretability in ...
Spark + AI Summit - The Importance of Model Fairness and Interpretability in ...Spark + AI Summit - The Importance of Model Fairness and Interpretability in ...
Spark + AI Summit - The Importance of Model Fairness and Interpretability in ...Francesca Lazzeri, PhD
 
Intro to machine learning
Intro to machine learningIntro to machine learning
Intro to machine learningTamir Taha
 
Barga Data Science lecture 10
Barga Data Science lecture 10Barga Data Science lecture 10
Barga Data Science lecture 10Roger Barga
 
Deep Credit Risk Ranking with LSTM with Kyle Grove
Deep Credit Risk Ranking with LSTM with Kyle GroveDeep Credit Risk Ranking with LSTM with Kyle Grove
Deep Credit Risk Ranking with LSTM with Kyle GroveDatabricks
 

Similar to The Dangers of Machine Learning (20)

Generative Adversarial Network (GAN)
Generative Adversarial Network (GAN)Generative Adversarial Network (GAN)
Generative Adversarial Network (GAN)
 
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018
Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018
 
Machine Learning Foundations for Professional Managers
Machine Learning Foundations for Professional ManagersMachine Learning Foundations for Professional Managers
Machine Learning Foundations for Professional Managers
 
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
 
Big Data Spain 2018: How to build Weighted XGBoost ML model for Imbalance dat...
Big Data Spain 2018: How to build Weighted XGBoost ML model for Imbalance dat...Big Data Spain 2018: How to build Weighted XGBoost ML model for Imbalance dat...
Big Data Spain 2018: How to build Weighted XGBoost ML model for Imbalance dat...
 
Hacking Predictive Modeling - RoadSec 2018
Hacking Predictive Modeling - RoadSec 2018Hacking Predictive Modeling - RoadSec 2018
Hacking Predictive Modeling - RoadSec 2018
 
Model evaluation in the land of deep learning
Model evaluation in the land of deep learningModel evaluation in the land of deep learning
Model evaluation in the land of deep learning
 
MLSS poster
MLSS posterMLSS poster
MLSS poster
 
Build, train, and deploy ML models with Amazon SageMaker - AIM302 - New York ...
Build, train, and deploy ML models with Amazon SageMaker - AIM302 - New York ...Build, train, and deploy ML models with Amazon SageMaker - AIM302 - New York ...
Build, train, and deploy ML models with Amazon SageMaker - AIM302 - New York ...
 
Engineering Machine Learning Data Pipelines Series: Big Data Quality - Cleans...
Engineering Machine Learning Data Pipelines Series: Big Data Quality - Cleans...Engineering Machine Learning Data Pipelines Series: Big Data Quality - Cleans...
Engineering Machine Learning Data Pipelines Series: Big Data Quality - Cleans...
 
The importance of model fairness and interpretability in AI systems
The importance of model fairness and interpretability in AI systemsThe importance of model fairness and interpretability in AI systems
The importance of model fairness and interpretability in AI systems
 
Choosing a Machine Learning technique to solve your need
Choosing a Machine Learning technique to solve your needChoosing a Machine Learning technique to solve your need
Choosing a Machine Learning technique to solve your need
 
High time to add machine learning to your information security stack
High time to add machine learning to your information security stackHigh time to add machine learning to your information security stack
High time to add machine learning to your information security stack
 
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
لموعد الإثنين 03 يناير 2022 143 مبادرة #تواصل_تطوير المحاضرة ال 143 من المباد...
 
Explainability and bias in AI
Explainability and bias in AIExplainability and bias in AI
Explainability and bias in AI
 
Spark + AI Summit - The Importance of Model Fairness and Interpretability in ...
Spark + AI Summit - The Importance of Model Fairness and Interpretability in ...Spark + AI Summit - The Importance of Model Fairness and Interpretability in ...
Spark + AI Summit - The Importance of Model Fairness and Interpretability in ...
 
Managing machine learning
Managing machine learningManaging machine learning
Managing machine learning
 
Intro to machine learning
Intro to machine learningIntro to machine learning
Intro to machine learning
 
Barga Data Science lecture 10
Barga Data Science lecture 10Barga Data Science lecture 10
Barga Data Science lecture 10
 
Deep Credit Risk Ranking with LSTM with Kyle Grove
Deep Credit Risk Ranking with LSTM with Kyle GroveDeep Credit Risk Ranking with LSTM with Kyle Grove
Deep Credit Risk Ranking with LSTM with Kyle Grove
 

Recently uploaded

%in ivory park+277-882-255-28 abortion pills for sale in ivory park
%in ivory park+277-882-255-28 abortion pills for sale in ivory park %in ivory park+277-882-255-28 abortion pills for sale in ivory park
%in ivory park+277-882-255-28 abortion pills for sale in ivory park masabamasaba
 
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...Shane Coughlan
 
VTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learnVTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learnAmarnathKambale
 
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...harshavardhanraghave
 
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisamasabamasaba
 
Right Money Management App For Your Financial Goals
Right Money Management App For Your Financial GoalsRight Money Management App For Your Financial Goals
Right Money Management App For Your Financial GoalsJhone kinadey
 
AI & Machine Learning Presentation Template
AI & Machine Learning Presentation TemplateAI & Machine Learning Presentation Template
AI & Machine Learning Presentation TemplatePresentation.STUDIO
 
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...masabamasaba
 
%+27788225528 love spells in Vancouver Psychic Readings, Attraction spells,Br...
%+27788225528 love spells in Vancouver Psychic Readings, Attraction spells,Br...%+27788225528 love spells in Vancouver Psychic Readings, Attraction spells,Br...
%+27788225528 love spells in Vancouver Psychic Readings, Attraction spells,Br...masabamasaba
 
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...SelfMade bd
 
Chinsurah Escorts ☎️8617697112 Starting From 5K to 15K High Profile Escorts ...
Chinsurah Escorts ☎️8617697112  Starting From 5K to 15K High Profile Escorts ...Chinsurah Escorts ☎️8617697112  Starting From 5K to 15K High Profile Escorts ...
Chinsurah Escorts ☎️8617697112 Starting From 5K to 15K High Profile Escorts ...Nitya salvi
 
AI Mastery 201: Elevating Your Workflow with Advanced LLM Techniques
AI Mastery 201: Elevating Your Workflow with Advanced LLM TechniquesAI Mastery 201: Elevating Your Workflow with Advanced LLM Techniques
AI Mastery 201: Elevating Your Workflow with Advanced LLM TechniquesVictorSzoltysek
 
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrainmasabamasaba
 
%in Midrand+277-882-255-28 abortion pills for sale in midrand
%in Midrand+277-882-255-28 abortion pills for sale in midrand%in Midrand+277-882-255-28 abortion pills for sale in midrand
%in Midrand+277-882-255-28 abortion pills for sale in midrandmasabamasaba
 
Unlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language ModelsUnlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language Modelsaagamshah0812
 
Software Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsSoftware Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsArshad QA
 
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️Delhi Call girls
 
Announcing Codolex 2.0 from GDK Software
Announcing Codolex 2.0 from GDK SoftwareAnnouncing Codolex 2.0 from GDK Software
Announcing Codolex 2.0 from GDK SoftwareJim McKeeth
 
10 Trends Likely to Shape Enterprise Technology in 2024
10 Trends Likely to Shape Enterprise Technology in 202410 Trends Likely to Shape Enterprise Technology in 2024
10 Trends Likely to Shape Enterprise Technology in 2024Mind IT Systems
 
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...Steffen Staab
 

Recently uploaded (20)

%in ivory park+277-882-255-28 abortion pills for sale in ivory park
%in ivory park+277-882-255-28 abortion pills for sale in ivory park %in ivory park+277-882-255-28 abortion pills for sale in ivory park
%in ivory park+277-882-255-28 abortion pills for sale in ivory park
 
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
 
VTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learnVTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learn
 
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
 
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
 
Right Money Management App For Your Financial Goals
Right Money Management App For Your Financial GoalsRight Money Management App For Your Financial Goals
Right Money Management App For Your Financial Goals
 
AI & Machine Learning Presentation Template
AI & Machine Learning Presentation TemplateAI & Machine Learning Presentation Template
AI & Machine Learning Presentation Template
 
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...
%+27788225528 love spells in Colorado Springs Psychic Readings, Attraction sp...
 
%+27788225528 love spells in Vancouver Psychic Readings, Attraction spells,Br...
%+27788225528 love spells in Vancouver Psychic Readings, Attraction spells,Br...%+27788225528 love spells in Vancouver Psychic Readings, Attraction spells,Br...
%+27788225528 love spells in Vancouver Psychic Readings, Attraction spells,Br...
 
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
Crypto Cloud Review - How To Earn Up To $500 Per DAY Of Bitcoin 100% On AutoP...
 
Chinsurah Escorts ☎️8617697112 Starting From 5K to 15K High Profile Escorts ...
Chinsurah Escorts ☎️8617697112  Starting From 5K to 15K High Profile Escorts ...Chinsurah Escorts ☎️8617697112  Starting From 5K to 15K High Profile Escorts ...
Chinsurah Escorts ☎️8617697112 Starting From 5K to 15K High Profile Escorts ...
 
AI Mastery 201: Elevating Your Workflow with Advanced LLM Techniques
AI Mastery 201: Elevating Your Workflow with Advanced LLM TechniquesAI Mastery 201: Elevating Your Workflow with Advanced LLM Techniques
AI Mastery 201: Elevating Your Workflow with Advanced LLM Techniques
 
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
 
%in Midrand+277-882-255-28 abortion pills for sale in midrand
%in Midrand+277-882-255-28 abortion pills for sale in midrand%in Midrand+277-882-255-28 abortion pills for sale in midrand
%in Midrand+277-882-255-28 abortion pills for sale in midrand
 
Unlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language ModelsUnlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language Models
 
Software Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsSoftware Quality Assurance Interview Questions
Software Quality Assurance Interview Questions
 
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
 
Announcing Codolex 2.0 from GDK Software
Announcing Codolex 2.0 from GDK SoftwareAnnouncing Codolex 2.0 from GDK Software
Announcing Codolex 2.0 from GDK Software
 
10 Trends Likely to Shape Enterprise Technology in 2024
10 Trends Likely to Shape Enterprise Technology in 202410 Trends Likely to Shape Enterprise Technology in 2024
10 Trends Likely to Shape Enterprise Technology in 2024
 
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
 

The Dangers of Machine Learning

  • 1. Kevin Smeyers Evolutionary Architect kevin.smeyers@tothepoint.company @ksmeyers 1 AI – Artificial Intelligence The Dangers M2Q – 01 April 2019
  • 2. • Adversarial attacks • Tricking Models • Reverse engineering of models (leaking information) • Poisoned data • Bias in data • Building the right model with the wrong conclusions • Ethics • Privacy? Using AI for good! • Deepfake • GPT2 • Security in general
  • 4.
  • 5.
  • 6.
  • 7. • High-Level Representation Guided Denoising • Adversarial training • Pixel Deflection • …. • Toolboxes • Advertorch – robustness tester • https://github.com/tensorflow/cleverhans • ….
  • 10. The square peg bias This is where you just choose the wrong data set because it's what you have. For example: You want model sportswear purchases for your online clothing store, but you only have data on what people have been buying at brick-and-mortar shops.
  • 11. Sampling bias You choose your data to represent an environment. Generally, you choose a subset of data that is representative and sufficiently large, but you have to watch out for the human biases in picking that data; it can be as innocent as forgetting to include nighttime data in a training set for facial recognition. http://beauty.ai https://www.techrepublic.com/article/top-10-ai-failures-of-2016/
  • 12. Bias-variance trade-off You may cause bias by overcorrecting for variance. If your model is too sensitive to variance, small fluctuations could cause it to model random noise. Too much bias to correct this could miss complexity. Nearest neighbor prediction regions. Lighter colors indicate less certainty about predictions. You can adjust the value of k. Value of k has direct impact on bias-variance trade-off
  • 13. Bias-variance trade-off You may cause bias by overcorrecting for variance. If your model is too sensitive to variance, small fluctuations could cause it to model random noise. Too much bias to correct this could miss complexity. Nearest neighbor prediction regions. Lighter colors indicate less certainty about predictions. You can adjust the value of k. Value of k has direct impact on bias-variance trade-off
  • 14. Bias-variance trade-off You may cause bias by overcorrecting for variance. If your model is too sensitive to variance, small fluctuations could cause it to model random noise. Too much bias to correct this could miss complexity. Nearest neighbor prediction regions. Lighter colors indicate less certainty about predictions. You can adjust the value of k. Value of k has direct impact on bias-variance trade-off
  • 15. Measurement bias This is when the device you use to collect the data has bias built in, like say a scale that incorrectly overestimates weight; so the data is sound, and no statistical correction would catch it. Having multiple measuring devices can help prevent this.
  • 16. Stereotype bias You're training a machine learning algorithm to recognize people at work, so you give it lots of images of male doctors and women teachers. This might even be mathematically sound, since the stereotype is social and might exist in the data without you even getting involved. But if you want a stronger ML, you'll need to correct for that social stereotype. https://arxiv.org/pdf/1607.06520.pdf man − woman ≈ computer programmer − homemaker.
  • 17. • Have objective acceptance criteria. Know the amount of error you and your users are willing to accept • Test with new data. • Don’t count on all results being accurate. • Understand the architecture of the network as a part of the testing process • Communicate the level of confidence you have in the results to management and users.
  • 18. • Model performance • Metamorphic testing • C. Murphy, G. E. Kaiser, L. Hu, and L. Wu, “Properties of Machine Learning Applications for Use in Metamorphic Testing,” in SEKE, 2008, vol. 8, pp. 867–872 • Driverless vehicle https://www.researchgate.net/publication/331289445_Metamorphic_testing_of_driverless_cars • Dual coding • Coverage guided fuzzing • TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing • Comparison with simplified, linear models • Testing with different data slices
  • 19. Alan Turing “if a machine is expected to be infallible, it cannot also be intelligent”
  • 20. Gary Kasparov (@AMLD2019) We aren’t be replaced, we are begin promoted
  • 21. Dr. Viviene Ming (@SuperNova) Good technology shouldn’t substitute what we do, it should make us better at doing it. Example Sexy Face
  • 22. Zeynep Tufekci (@AMLD2019) #ML and #AI surfacing and exploiting #biases that we are not even aware of — because we had no way to identify them at scale Asking them for open ending questions….