SlideShare ist ein Scribd-Unternehmen logo
1 von 25
Downloaden Sie, um offline zu lesen
© 2017 The MITRE Corporation. All rights reserved.
Chuck	Howell,	howell@mitre.org
23	March	2017
“Fairness	Cases”	as	an	Accelerant	
and	Enabler	for	Cognitive	Assistance	
Adoption*
| 2 |
© 2017 The MITRE Corporation. All rights reserved.
Beware Disappointed Football Fans…
| 3 |
© 2017 The MITRE Corporation. All rights reserved.
Justice Delayed is Justice Denied
| 4 |
© 2017 The MITRE Corporation. All rights reserved.
Solution: Cool Dispassionate AI?
| 5 |
© 2017 The MITRE Corporation. All rights reserved.
Doh!
| 6 |
© 2017 The MITRE Corporation. All rights reserved.
Doh!
OSTP	Preparing	for	the	Future	of	AI	section	on	Fairness,	Safety,	and	Governance:
As	AI	technologies	gain	broader	deployment,	technical	experts	and	policy	analysts	have	raised	
concerns	about	unintended	consequences.	The	use	of	AI	to	make	consequential	decisions	about	
people,	often	replacing	decisions	made	by	human	actors	and	institutions,	leads	to	concerns	about	
how	to	ensure	justice,	fairness,	and	accountability.
| 7 |
© 2017 The MITRE Corporation. All rights reserved.
Proof by repeated assertion (1 of 2)
As AI systems take on a more important role in
high-stakes decision-making – from offers of
credit and insurance, to hiring decisions and
parole – they will begin to affect who gets
offered crucial opportunities, and who is left
behind. This brings questions of rights,
liberties, and basic fairness to the forefront.
While some hope that AI systems will help to
overcome the biases that plague human
decision-making, others fear that AI systems
will amplify such biases, denying opportunities
to the deserving and subjecting the deprived to
further disadvantage.
| 8 |
© 2017 The MITRE Corporation. All rights reserved.
Proof by repeated assertion (2 of 2)
http://www.fatml.org
| 9 |
© 2017 The MITRE Corporation. All rights reserved.
Assertions
§ Adoption of AI in decision support and other Cognitive
Assistance roles is growing significantly, and pace of
adoption continues to increase
§ Concerns expressed about risks of implicit bias and
discrimination
§ Point solutions being explored
§ Desired: broad systems engineering framework for calibrating
and mitigating fairness risks in AI systems
§ Adopting/adapting tools and techniques from safety critical
software community is one opportunity
| 10 |
© 2017 The MITRE Corporation. All rights reserved.
Safety Critical Software
§ Software is a key part of a variety of critical
systems, requiring systematic and effective
techniques for assurance that the risks of
deploying are understood and acceptable
§ Safety Critical Software: Software for which
compelling evidence is required that it delivers a
specified set of services in a manner that satisfies
specified critical properties tied to safety.
“Engineers today, like Galileo three and a half centuries ago, are not superhuman.
They make mistakes in their assumptions, in their calculations, in their conclusions.
That they make mistakes is forgivable; that they catch them is imperative. Thus it
is the essence of modern engineering not only to be able to check one’s own work,
but also to have one’s work checked and to be able to check the work of others.”
-- H. Petroski in To Engineer is Human: The Role of Failure in Successful Design
| 11 |
© 2017 The MITRE Corporation. All rights reserved.
Multiple Stakeholders for Safety
Source:	
Andy
Lacher,	
MITRE
| 12 |
© 2017 The MITRE Corporation. All rights reserved.
System properties vs. specific actions
§ Assessment of the system prior to operation
– Various stakeholders: Are the risks of allowing this system to be
used understood, and justified by the benefits?
– Certification, acceptance tests, standards compliance, etc.
§ Assessment of the results of operation
– Various stakeholders: Have the claims made prior to operation
been justified? Do the benefits justify the current understanding of
risks?
– Instrumentation, mishap investigation, audit, etc.
| 13 |
© 2017 The MITRE Corporation. All rights reserved.
Some exchanges between AI and
safety communities
But	much	more	to	do,	and	adapting	to	other	critical	concerns	is	only	starting
| 14 |
© 2017 The MITRE Corporation. All rights reserved.
No silver bullet, but tools and notations
matter…
÷ vs.
| 15 |
© 2017 The MITRE Corporation. All rights reserved.
Examples of opportunities to adapt
safety tools and techniques
§ Fairness case framework to organize all activity and
communicate to various stakeholders
§ Hazard analysis to expose potential threats to fairness (obvious
and unexpected sources)
§ Instrumentation and monitoring tools and techniques to detect
potential fairness violations in operation
§ Accident and incident investigation tools and techniques to
understand underlying causes of a fairness violation
§ Error handling frameworks to focus engineering attention on off-
nominal cases, where problems often lurk
| 16 |
© 2017 The MITRE Corporation. All rights reserved.
What is an “Assurance Case”?
§ Systems under regulation or acquisition constraints
– Third party certification, approval, licensing, etc.
– Require a documented body of evidence that provides a
compelling case that the system satisfies certain critical
properties for specific contexts (to “make the case”)
– “safety case”, “certification evidence”, “security case”…
– Collectively we’ll refer to them as “assurance cases”
A documented body of evidence that provides a convincing and valid argument
that a specified set of critical claims about a system’s properties are adequately
justified for a given system in a given environment.
| 17 |
© 2017 The MITRE Corporation. All rights reserved.
What does tool support look like?
| 18 |
© 2017 The MITRE Corporation. All rights reserved.
Hazard Analysis Tools
§ Standards for regulated safety-critical sectors require specific
techniques for assessing the potential hazards of proposed
systems. These techniques often focus on individual
component failures and their associated reliability. More recent
techniques such as the Systems-Theoretic Process Analysis
(STPA) view safety as a system-level property, and accidents as
a control problem not a component reliability problem.
§ Other emerging techniques such as Hierarchically Performed
Hazard Origin & Propagation Studies (HiP-HOPS)
§ Explicitly and deliberately exploring potential fairness violations
at the start could contribute to confidence in the overall fairness
case, influence system design, and reduce rework
| 19 |
© 2017 The MITRE Corporation. All rights reserved.
Hazard analysis for fairness
§ Force early consideration of well known categories of potential
problems and how they will be addressed
– e.g., statistical equivalence of training data wrt operational data
(“Robustness to Distributional Change”1)
§ Focus on what aviation industry calls “hazardous misleading
information” not just overt failure
1Concrete	Problems	in	AI	Safety,	https://arxiv.org/abs/1606.06565#
| 20 |
© 2017 The MITRE Corporation. All rights reserved.
Accident Investigation Tools and
Notations
§ Working back from an incident or accident to root causes can be
extremely expensive and complex
– Millions of $s, years of effort
– Consequences of false positive and negative findings
– Tools and notations have evolved to help manage the data, do
“book keeping” and structural checks, and communicate
complicated findings
§ Screenshots of a few follow, but the key ideas are that they are
intended to support a collaborative team working backwards
from a rare event through a complex, subtle, and incomplete sea
of data to root causes: investigation and diagnosis
| 21 |
© 2017 The MITRE Corporation. All rights reserved.
NASA Multi-User Investigation
Organizer
| 22 |
© 2017 The MITRE Corporation. All rights reserved.
Why-Because Analysis Graphs
| 23 |
© 2017 The MITRE Corporation. All rights reserved.
Conclusion
§ Painfully obvious early days of a work in progress
– Please help correct errors of omission and commission, all
feedback very much appreciated
§ Cognitive assistance presents opportunities for great social
good, but concerns over fairness present possible impediment
§ Integrated collection of tools and techniques from safety critical
software community is worth assessing
– What can be readily adopted? Adapted, and how? What are gaps
that require completely new tools and techniques?
| 24 |
© 2017 The MITRE Corporation. All rights reserved.
Closing Credits
“They	constantly	try	to	escape...	by	dreaming	of	systems	so	perfect	that	
no	one	will	need	to	be	good”						
T.	S.	Eliot,	Choruses	from	"The	Rock",	VI
“Be	careful	how	you	fix	what	you	don't	understand.”	
Fred	Brooks,	The	Design	of	Design
Thank you!
© 2017 The MITRE Corporation. All rights reserved.
| 25 |
Backups

Weitere ähnliche Inhalte

Was ist angesagt?

Healthcare Cybersecurity Whitepaper FINAL
Healthcare Cybersecurity Whitepaper FINALHealthcare Cybersecurity Whitepaper FINAL
Healthcare Cybersecurity Whitepaper FINAL
Steve Knapp
 
Sans 20 CSC: Connecting Security to the Business Mission
Sans 20 CSC: Connecting Security to the Business MissionSans 20 CSC: Connecting Security to the Business Mission
Sans 20 CSC: Connecting Security to the Business Mission
Tripwire
 
NIST Cybersecurity Framework Background and Review | Jack Whitsitt
NIST Cybersecurity Framework Background and Review | Jack WhitsittNIST Cybersecurity Framework Background and Review | Jack Whitsitt
NIST Cybersecurity Framework Background and Review | Jack Whitsitt
Jack Whitsitt
 
2014 Data Protection Maturity Survey: Results and Analysis
2014 Data Protection Maturity Survey: Results and Analysis2014 Data Protection Maturity Survey: Results and Analysis
2014 Data Protection Maturity Survey: Results and Analysis
Lumension
 

Was ist angesagt? (20)

A koene ai_in_command_control
A koene ai_in_command_controlA koene ai_in_command_control
A koene ai_in_command_control
 
Spring Splash 3.4.2019: When AI Meets Ethics by Meeri Haataja
Spring Splash 3.4.2019: When AI Meets Ethics by Meeri Haataja Spring Splash 3.4.2019: When AI Meets Ethics by Meeri Haataja
Spring Splash 3.4.2019: When AI Meets Ethics by Meeri Haataja
 
Healthcare Cybersecurity Whitepaper FINAL
Healthcare Cybersecurity Whitepaper FINALHealthcare Cybersecurity Whitepaper FINAL
Healthcare Cybersecurity Whitepaper FINAL
 
Cyber Table Top Exercise -- Model Roadmap
Cyber Table Top Exercise -- Model RoadmapCyber Table Top Exercise -- Model Roadmap
Cyber Table Top Exercise -- Model Roadmap
 
Sans 20 CSC: Connecting Security to the Business Mission
Sans 20 CSC: Connecting Security to the Business MissionSans 20 CSC: Connecting Security to the Business Mission
Sans 20 CSC: Connecting Security to the Business Mission
 
How to measure your cybersecurity performance
How to measure your cybersecurity performanceHow to measure your cybersecurity performance
How to measure your cybersecurity performance
 
2018 Adobe Cybersecurity Survey
2018 Adobe Cybersecurity Survey2018 Adobe Cybersecurity Survey
2018 Adobe Cybersecurity Survey
 
Information Technology Vendor Risk Management
Information Technology Vendor Risk ManagementInformation Technology Vendor Risk Management
Information Technology Vendor Risk Management
 
Ivanti Threat Thursday for April 30
Ivanti Threat Thursday for April 30Ivanti Threat Thursday for April 30
Ivanti Threat Thursday for April 30
 
Responsible AI: An Example AI Development Process with Focus on Risks and Con...
Responsible AI: An Example AI Development Process with Focus on Risks and Con...Responsible AI: An Example AI Development Process with Focus on Risks and Con...
Responsible AI: An Example AI Development Process with Focus on Risks and Con...
 
Strengthening Security with Continuous Monitoring
Strengthening Security with Continuous MonitoringStrengthening Security with Continuous Monitoring
Strengthening Security with Continuous Monitoring
 
Priming your digital immune system: Cybersecurity in the cognitive era
Priming your digital immune system: Cybersecurity in the cognitive eraPriming your digital immune system: Cybersecurity in the cognitive era
Priming your digital immune system: Cybersecurity in the cognitive era
 
Master Class Cyber Compliance IE Law School IE Busines School
Master Class Cyber Compliance IE Law School IE Busines SchoolMaster Class Cyber Compliance IE Law School IE Busines School
Master Class Cyber Compliance IE Law School IE Busines School
 
2013 Data Protection Maturity Trends: How Do You Compare?
2013 Data Protection Maturity Trends: How Do You Compare?2013 Data Protection Maturity Trends: How Do You Compare?
2013 Data Protection Maturity Trends: How Do You Compare?
 
Get it Together: ChainLink Securely Tying Smart Contracts to the Data They Re...
Get it Together: ChainLink Securely Tying Smart Contracts to the Data They Re...Get it Together: ChainLink Securely Tying Smart Contracts to the Data They Re...
Get it Together: ChainLink Securely Tying Smart Contracts to the Data They Re...
 
Tunnel Vision Is Hurting Your Security: Time to See the Forest for the Trees
Tunnel Vision Is Hurting Your Security: Time to See the Forest for the TreesTunnel Vision Is Hurting Your Security: Time to See the Forest for the Trees
Tunnel Vision Is Hurting Your Security: Time to See the Forest for the Trees
 
when minutes counts
when minutes countswhen minutes counts
when minutes counts
 
NIST Cybersecurity Framework Background and Review | Jack Whitsitt
NIST Cybersecurity Framework Background and Review | Jack WhitsittNIST Cybersecurity Framework Background and Review | Jack Whitsitt
NIST Cybersecurity Framework Background and Review | Jack Whitsitt
 
2014 Data Protection Maturity Survey: Results and Analysis
2014 Data Protection Maturity Survey: Results and Analysis2014 Data Protection Maturity Survey: Results and Analysis
2014 Data Protection Maturity Survey: Results and Analysis
 
Cyber Security Infographic
Cyber Security InfographicCyber Security Infographic
Cyber Security Infographic
 

Andere mochten auch

Andere mochten auch (14)

Favourite Photo Shoot Photos
Favourite Photo Shoot Photos Favourite Photo Shoot Photos
Favourite Photo Shoot Photos
 
зст
зстзст
зст
 
Ikip pgri-pontianak
Ikip pgri-pontianakIkip pgri-pontianak
Ikip pgri-pontianak
 
TUVALU COUNTRY
TUVALU COUNTRYTUVALU COUNTRY
TUVALU COUNTRY
 
тема урока
тема урокатема урока
тема урока
 
9 кла бун рус яз
9 кла бун рус яз9 кла бун рус яз
9 кла бун рус яз
 
Fintech 2017 Vision and Insight - MIT Enterprise Forum Poland
Fintech 2017 Vision and Insight - MIT Enterprise Forum PolandFintech 2017 Vision and Insight - MIT Enterprise Forum Poland
Fintech 2017 Vision and Insight - MIT Enterprise Forum Poland
 
Opus grammar tips
Opus grammar tipsOpus grammar tips
Opus grammar tips
 
Java Security Framework's
Java Security Framework'sJava Security Framework's
Java Security Framework's
 
Communication and media response to the Westminster Attack
Communication and media response to the Westminster AttackCommunication and media response to the Westminster Attack
Communication and media response to the Westminster Attack
 
Urban Transitions Shanghai 2016 Welcome Slides
Urban Transitions Shanghai 2016 Welcome SlidesUrban Transitions Shanghai 2016 Welcome Slides
Urban Transitions Shanghai 2016 Welcome Slides
 
Dockland musesum visit
Dockland musesum visit Dockland musesum visit
Dockland musesum visit
 
"Ігрова діяльність у групі продовженого дня". Доповідь на педраді
"Ігрова діяльність у групі продовженого дня". Доповідь на педраді"Ігрова діяльність у групі продовженого дня". Доповідь на педраді
"Ігрова діяльність у групі продовженого дня". Доповідь на педраді
 
IRREGULARES EN EL SISTEMA DE SALUD EN COLOMBIA
IRREGULARES EN EL SISTEMA DE SALUD EN COLOMBIAIRREGULARES EN EL SISTEMA DE SALUD EN COLOMBIA
IRREGULARES EN EL SISTEMA DE SALUD EN COLOMBIA
 

Ähnlich wie “Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”

Assembling-Accountability.pdf
Assembling-Accountability.pdfAssembling-Accountability.pdf
Assembling-Accountability.pdf
ssusere0ee1d
 

Ähnlich wie “Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption” (20)

AI Governance and Ethics - Industry Standards
AI Governance and Ethics - Industry StandardsAI Governance and Ethics - Industry Standards
AI Governance and Ethics - Industry Standards
 
[Webinar] Supercharging Security with Behavioral Analytics
[Webinar] Supercharging Security with Behavioral Analytics[Webinar] Supercharging Security with Behavioral Analytics
[Webinar] Supercharging Security with Behavioral Analytics
 
Operationalizing Big Data Security Analytics - IANS Forum Dallas
Operationalizing Big Data Security Analytics - IANS Forum DallasOperationalizing Big Data Security Analytics - IANS Forum Dallas
Operationalizing Big Data Security Analytics - IANS Forum Dallas
 
Assembling-Accountability.pdf
Assembling-Accountability.pdfAssembling-Accountability.pdf
Assembling-Accountability.pdf
 
Role of AI Safety Institutes in Trustworthy AI.pdf
Role of AI Safety Institutes in Trustworthy AI.pdfRole of AI Safety Institutes in Trustworthy AI.pdf
Role of AI Safety Institutes in Trustworthy AI.pdf
 
Accenture 2017 Global Risk Study: Capital Markets Summary
Accenture 2017 Global Risk Study: Capital Markets SummaryAccenture 2017 Global Risk Study: Capital Markets Summary
Accenture 2017 Global Risk Study: Capital Markets Summary
 
Operationalizing Big Data Security Analytics - IANS Forum Toronto Keynote
Operationalizing Big Data Security Analytics - IANS Forum Toronto KeynoteOperationalizing Big Data Security Analytics - IANS Forum Toronto Keynote
Operationalizing Big Data Security Analytics - IANS Forum Toronto Keynote
 
A New Approach to Threat Detection: Big Data Security Analytics
A New Approach to Threat Detection: Big Data Security Analytics A New Approach to Threat Detection: Big Data Security Analytics
A New Approach to Threat Detection: Big Data Security Analytics
 
Incidents - The Shorter, the Better with the Quality Engineering Discipline
Incidents - The Shorter, the Better with the Quality Engineering DisciplineIncidents - The Shorter, the Better with the Quality Engineering Discipline
Incidents - The Shorter, the Better with the Quality Engineering Discipline
 
Algorithmically Mediated Online Inforamtion Access workshop at WebSci17
Algorithmically Mediated Online Inforamtion Access workshop at WebSci17Algorithmically Mediated Online Inforamtion Access workshop at WebSci17
Algorithmically Mediated Online Inforamtion Access workshop at WebSci17
 
Data Connectors San Antonio Cybersecurity Conference 2018
Data Connectors San Antonio Cybersecurity Conference 2018Data Connectors San Antonio Cybersecurity Conference 2018
Data Connectors San Antonio Cybersecurity Conference 2018
 
Cyber Threat Intelligence: Transforming Data into Relevant Intelligence
Cyber Threat Intelligence: Transforming Data into Relevant IntelligenceCyber Threat Intelligence: Transforming Data into Relevant Intelligence
Cyber Threat Intelligence: Transforming Data into Relevant Intelligence
 
How to Operationalize Big Data Security Analytics
How to Operationalize Big Data Security AnalyticsHow to Operationalize Big Data Security Analytics
How to Operationalize Big Data Security Analytics
 
How to Operationalize Big Data Security Analytics
How to Operationalize Big Data Security AnalyticsHow to Operationalize Big Data Security Analytics
How to Operationalize Big Data Security Analytics
 
Trust, Context and, Regulation: Achieving More Explainable AI in Financial Se...
Trust, Context and, Regulation: Achieving More Explainable AI in Financial Se...Trust, Context and, Regulation: Achieving More Explainable AI in Financial Se...
Trust, Context and, Regulation: Achieving More Explainable AI in Financial Se...
 
HARNESSING AI FOR ENHANCED MEDIA ANALYSIS A CASE STUDY ON CHATGPT AT DRONE EM...
HARNESSING AI FOR ENHANCED MEDIA ANALYSIS A CASE STUDY ON CHATGPT AT DRONE EM...HARNESSING AI FOR ENHANCED MEDIA ANALYSIS A CASE STUDY ON CHATGPT AT DRONE EM...
HARNESSING AI FOR ENHANCED MEDIA ANALYSIS A CASE STUDY ON CHATGPT AT DRONE EM...
 
WEBINAR: How To Use Artificial Intelligence To Prevent Insider Threats
WEBINAR: How To Use Artificial Intelligence To Prevent Insider ThreatsWEBINAR: How To Use Artificial Intelligence To Prevent Insider Threats
WEBINAR: How To Use Artificial Intelligence To Prevent Insider Threats
 
The Myths + Realities of Machine-Learning Cybersecurity
The Myths + Realities of Machine-Learning CybersecurityThe Myths + Realities of Machine-Learning Cybersecurity
The Myths + Realities of Machine-Learning Cybersecurity
 
Machine Learning: Addressing the Disillusionment to Bring Actual Business Ben...
Machine Learning: Addressing the Disillusionment to Bring Actual Business Ben...Machine Learning: Addressing the Disillusionment to Bring Actual Business Ben...
Machine Learning: Addressing the Disillusionment to Bring Actual Business Ben...
 
Machine Learning for Auditors
Machine Learning for AuditorsMachine Learning for Auditors
Machine Learning for Auditors
 

Mehr von diannepatricia

Mehr von diannepatricia (20)

Teaching cognitive computing with ibm watson
Teaching cognitive computing with ibm watsonTeaching cognitive computing with ibm watson
Teaching cognitive computing with ibm watson
 
Cognitive systems institute talk 8 june 2017 - v.1.0
Cognitive systems institute talk   8 june 2017 - v.1.0Cognitive systems institute talk   8 june 2017 - v.1.0
Cognitive systems institute talk 8 june 2017 - v.1.0
 
Building Compassionate Conversational Systems
Building Compassionate Conversational SystemsBuilding Compassionate Conversational Systems
Building Compassionate Conversational Systems
 
“Artificial Intelligence, Cognitive Computing and Innovating in Practice”
“Artificial Intelligence, Cognitive Computing and Innovating in Practice”“Artificial Intelligence, Cognitive Computing and Innovating in Practice”
“Artificial Intelligence, Cognitive Computing and Innovating in Practice”
 
Cognitive Insights drive self-driving Accessibility
Cognitive Insights drive self-driving AccessibilityCognitive Insights drive self-driving Accessibility
Cognitive Insights drive self-driving Accessibility
 
Artificial Intellingence in the Car
Artificial Intellingence in the CarArtificial Intellingence in the Car
Artificial Intellingence in the Car
 
“Semantic PDF Processing & Document Representation”
“Semantic PDF Processing & Document Representation”“Semantic PDF Processing & Document Representation”
“Semantic PDF Processing & Document Representation”
 
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...
Joining Industry and Students for Cognitive Solutions at Karlsruhe Services R...
 
170330 cognitive systems institute speaker series mark sherman - watson pr...
170330 cognitive systems institute speaker series    mark sherman - watson pr...170330 cognitive systems institute speaker series    mark sherman - watson pr...
170330 cognitive systems institute speaker series mark sherman - watson pr...
 
Cognitive Assistance for the Aging
Cognitive Assistance for the AgingCognitive Assistance for the Aging
Cognitive Assistance for the Aging
 
From complex Systems to Networks: Discovering and Modeling the Correct Network"
From complex Systems to Networks: Discovering and Modeling the Correct Network"From complex Systems to Networks: Discovering and Modeling the Correct Network"
From complex Systems to Networks: Discovering and Modeling the Correct Network"
 
The Role of Dialog in Augmented Intelligence
The Role of Dialog in Augmented IntelligenceThe Role of Dialog in Augmented Intelligence
The Role of Dialog in Augmented Intelligence
 
Developing Cognitive Systems to Support Team Cognition
Developing Cognitive Systems to Support Team CognitionDeveloping Cognitive Systems to Support Team Cognition
Developing Cognitive Systems to Support Team Cognition
 
Cyber-Social Learning Systems
Cyber-Social Learning SystemsCyber-Social Learning Systems
Cyber-Social Learning Systems
 
“IT Technology Trends in 2017… and Beyond”
“IT Technology Trends in 2017… and Beyond”“IT Technology Trends in 2017… and Beyond”
“IT Technology Trends in 2017… and Beyond”
 
"Curious Learning: using a mobile platform for early literacy education as a ...
"Curious Learning: using a mobile platform for early literacy education as a ..."Curious Learning: using a mobile platform for early literacy education as a ...
"Curious Learning: using a mobile platform for early literacy education as a ...
 
Embodied Cognition - Booch HICSS50
Embodied Cognition - Booch HICSS50Embodied Cognition - Booch HICSS50
Embodied Cognition - Booch HICSS50
 
KATE - a Platform for Machine Learning
KATE - a Platform for Machine LearningKATE - a Platform for Machine Learning
KATE - a Platform for Machine Learning
 
Cognitive Computing for Aging Society
Cognitive Computing for Aging SocietyCognitive Computing for Aging Society
Cognitive Computing for Aging Society
 
Hicss17 asakawa
Hicss17 asakawaHicss17 asakawa
Hicss17 asakawa
 

Kürzlich hochgeladen

Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Victor Rentea
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
?#DUbAI#??##{{(☎️+971_581248768%)**%*]'#abortion pills for sale in dubai@
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Victor Rentea
 

Kürzlich hochgeladen (20)

Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
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
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024Finding Java's Hidden Performance Traps @ DevoxxUK 2024
Finding Java's Hidden Performance Traps @ DevoxxUK 2024
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
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...
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Platformless Horizons for Digital Adaptability
Platformless Horizons for Digital AdaptabilityPlatformless Horizons for Digital Adaptability
Platformless Horizons for Digital Adaptability
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
 
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, ...
 
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot ModelMcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Mcleodganj Call Girls 🥰 8617370543 Service Offer VIP Hot Model
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 

“Fairness Cases as an Accelerant and Enabler for Cognitive Assistance Adoption”

  • 1. © 2017 The MITRE Corporation. All rights reserved. Chuck Howell, howell@mitre.org 23 March 2017 “Fairness Cases” as an Accelerant and Enabler for Cognitive Assistance Adoption*
  • 2. | 2 | © 2017 The MITRE Corporation. All rights reserved. Beware Disappointed Football Fans…
  • 3. | 3 | © 2017 The MITRE Corporation. All rights reserved. Justice Delayed is Justice Denied
  • 4. | 4 | © 2017 The MITRE Corporation. All rights reserved. Solution: Cool Dispassionate AI?
  • 5. | 5 | © 2017 The MITRE Corporation. All rights reserved. Doh!
  • 6. | 6 | © 2017 The MITRE Corporation. All rights reserved. Doh! OSTP Preparing for the Future of AI section on Fairness, Safety, and Governance: As AI technologies gain broader deployment, technical experts and policy analysts have raised concerns about unintended consequences. The use of AI to make consequential decisions about people, often replacing decisions made by human actors and institutions, leads to concerns about how to ensure justice, fairness, and accountability.
  • 7. | 7 | © 2017 The MITRE Corporation. All rights reserved. Proof by repeated assertion (1 of 2) As AI systems take on a more important role in high-stakes decision-making – from offers of credit and insurance, to hiring decisions and parole – they will begin to affect who gets offered crucial opportunities, and who is left behind. This brings questions of rights, liberties, and basic fairness to the forefront. While some hope that AI systems will help to overcome the biases that plague human decision-making, others fear that AI systems will amplify such biases, denying opportunities to the deserving and subjecting the deprived to further disadvantage.
  • 8. | 8 | © 2017 The MITRE Corporation. All rights reserved. Proof by repeated assertion (2 of 2) http://www.fatml.org
  • 9. | 9 | © 2017 The MITRE Corporation. All rights reserved. Assertions § Adoption of AI in decision support and other Cognitive Assistance roles is growing significantly, and pace of adoption continues to increase § Concerns expressed about risks of implicit bias and discrimination § Point solutions being explored § Desired: broad systems engineering framework for calibrating and mitigating fairness risks in AI systems § Adopting/adapting tools and techniques from safety critical software community is one opportunity
  • 10. | 10 | © 2017 The MITRE Corporation. All rights reserved. Safety Critical Software § Software is a key part of a variety of critical systems, requiring systematic and effective techniques for assurance that the risks of deploying are understood and acceptable § Safety Critical Software: Software for which compelling evidence is required that it delivers a specified set of services in a manner that satisfies specified critical properties tied to safety. “Engineers today, like Galileo three and a half centuries ago, are not superhuman. They make mistakes in their assumptions, in their calculations, in their conclusions. That they make mistakes is forgivable; that they catch them is imperative. Thus it is the essence of modern engineering not only to be able to check one’s own work, but also to have one’s work checked and to be able to check the work of others.” -- H. Petroski in To Engineer is Human: The Role of Failure in Successful Design
  • 11. | 11 | © 2017 The MITRE Corporation. All rights reserved. Multiple Stakeholders for Safety Source: Andy Lacher, MITRE
  • 12. | 12 | © 2017 The MITRE Corporation. All rights reserved. System properties vs. specific actions § Assessment of the system prior to operation – Various stakeholders: Are the risks of allowing this system to be used understood, and justified by the benefits? – Certification, acceptance tests, standards compliance, etc. § Assessment of the results of operation – Various stakeholders: Have the claims made prior to operation been justified? Do the benefits justify the current understanding of risks? – Instrumentation, mishap investigation, audit, etc.
  • 13. | 13 | © 2017 The MITRE Corporation. All rights reserved. Some exchanges between AI and safety communities But much more to do, and adapting to other critical concerns is only starting
  • 14. | 14 | © 2017 The MITRE Corporation. All rights reserved. No silver bullet, but tools and notations matter… ÷ vs.
  • 15. | 15 | © 2017 The MITRE Corporation. All rights reserved. Examples of opportunities to adapt safety tools and techniques § Fairness case framework to organize all activity and communicate to various stakeholders § Hazard analysis to expose potential threats to fairness (obvious and unexpected sources) § Instrumentation and monitoring tools and techniques to detect potential fairness violations in operation § Accident and incident investigation tools and techniques to understand underlying causes of a fairness violation § Error handling frameworks to focus engineering attention on off- nominal cases, where problems often lurk
  • 16. | 16 | © 2017 The MITRE Corporation. All rights reserved. What is an “Assurance Case”? § Systems under regulation or acquisition constraints – Third party certification, approval, licensing, etc. – Require a documented body of evidence that provides a compelling case that the system satisfies certain critical properties for specific contexts (to “make the case”) – “safety case”, “certification evidence”, “security case”… – Collectively we’ll refer to them as “assurance cases” A documented body of evidence that provides a convincing and valid argument that a specified set of critical claims about a system’s properties are adequately justified for a given system in a given environment.
  • 17. | 17 | © 2017 The MITRE Corporation. All rights reserved. What does tool support look like?
  • 18. | 18 | © 2017 The MITRE Corporation. All rights reserved. Hazard Analysis Tools § Standards for regulated safety-critical sectors require specific techniques for assessing the potential hazards of proposed systems. These techniques often focus on individual component failures and their associated reliability. More recent techniques such as the Systems-Theoretic Process Analysis (STPA) view safety as a system-level property, and accidents as a control problem not a component reliability problem. § Other emerging techniques such as Hierarchically Performed Hazard Origin & Propagation Studies (HiP-HOPS) § Explicitly and deliberately exploring potential fairness violations at the start could contribute to confidence in the overall fairness case, influence system design, and reduce rework
  • 19. | 19 | © 2017 The MITRE Corporation. All rights reserved. Hazard analysis for fairness § Force early consideration of well known categories of potential problems and how they will be addressed – e.g., statistical equivalence of training data wrt operational data (“Robustness to Distributional Change”1) § Focus on what aviation industry calls “hazardous misleading information” not just overt failure 1Concrete Problems in AI Safety, https://arxiv.org/abs/1606.06565#
  • 20. | 20 | © 2017 The MITRE Corporation. All rights reserved. Accident Investigation Tools and Notations § Working back from an incident or accident to root causes can be extremely expensive and complex – Millions of $s, years of effort – Consequences of false positive and negative findings – Tools and notations have evolved to help manage the data, do “book keeping” and structural checks, and communicate complicated findings § Screenshots of a few follow, but the key ideas are that they are intended to support a collaborative team working backwards from a rare event through a complex, subtle, and incomplete sea of data to root causes: investigation and diagnosis
  • 21. | 21 | © 2017 The MITRE Corporation. All rights reserved. NASA Multi-User Investigation Organizer
  • 22. | 22 | © 2017 The MITRE Corporation. All rights reserved. Why-Because Analysis Graphs
  • 23. | 23 | © 2017 The MITRE Corporation. All rights reserved. Conclusion § Painfully obvious early days of a work in progress – Please help correct errors of omission and commission, all feedback very much appreciated § Cognitive assistance presents opportunities for great social good, but concerns over fairness present possible impediment § Integrated collection of tools and techniques from safety critical software community is worth assessing – What can be readily adopted? Adapted, and how? What are gaps that require completely new tools and techniques?
  • 24. | 24 | © 2017 The MITRE Corporation. All rights reserved. Closing Credits “They constantly try to escape... by dreaming of systems so perfect that no one will need to be good” T. S. Eliot, Choruses from "The Rock", VI “Be careful how you fix what you don't understand.” Fred Brooks, The Design of Design Thank you!
  • 25. © 2017 The MITRE Corporation. All rights reserved. | 25 | Backups