zenon/trustworthy-ai
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Add cognitive and non-cognitive trust

Browse Source
This commit is contained in:
Tobias Eidelpes 2021-12-14 14:36:26 +01:00
parent fea362696d
commit eefe4ae212
1 changed files with 160 additions and 124 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

284
trustworthy-ai.tex
View File

@ -1,124 +1,160 @@
\documentclass[runningheads]{llncs} \documentclass[runningheads]{llncs}
\usepackage{graphicx} \usepackage{graphicx}
\usepackage[backend=biber,style=numeric]{biblatex} \usepackage[backend=biber,style=numeric]{biblatex}
\usepackage{hyperref} \usepackage{hyperref}
\hypersetup{ \hypersetup{
colorlinks=true, colorlinks=true,
linkcolor=black, linkcolor=black,
urlcolor=blue, urlcolor=blue,
citecolor=black citecolor=black
} }
\addbibresource{trustworthy-ai.bib} \addbibresource{trustworthy-ai.bib}
\begin{document} \begin{document}
\title{Trustworthy Artificial Intelligence} \title{Trustworthy Artificial Intelligence}
\author{Tobias Eidelpes} \author{Tobias Eidelpes}
\authorrunning{T. Eidelpes} \authorrunning{T. Eidelpes}
\institute{Technische Universität Wien, Karlsplatz 13, 1040 Wien, Austria \institute{Technische Universität Wien, Karlsplatz 13, 1040 Wien, Austria
\email{e1527193@student.tuwien.ac.at}} \email{e1527193@student.tuwien.ac.at}}
\maketitle \maketitle
\begin{abstract} \begin{abstract}
The abstract should briefly summarize the contents of the paper in The abstract should briefly summarize the contents of the paper in
150--250 words. 150--250 words.
\keywords{Artificial Intelligence, Trustworthiness, Social Computing} \keywords{Artificial Intelligence, Trustworthiness, Social Computing}
\end{abstract} \end{abstract}
\section{Introduction} \section{Introduction}
\label{sec:introduction} \label{sec:introduction}
The use of artificial intelligence (AI) in computing has seen an unprecedented The use of artificial intelligence (AI) in computing has seen an unprecedented
rise over the last few years. From humble beginnings as a tool to aid humans in rise over the last few years. From humble beginnings as a tool to aid humans in
decision making to advanced use cases where human interaction is avoided as much decision making to advanced use cases where human interaction is avoided as much
as possible, AI has transformed the way we live our lives today. The as possible, AI has transformed the way we live our lives today. The
transformative capabilities of AI are not just felt in the area of computer transformative capabilities of AI are not just felt in the area of computer
science, but have bled into a diverse set of other disciplines such as biology, science, but have bled into a diverse set of other disciplines such as biology,
chemistry, mathematics and economics. For the purposes of this work, AIs are chemistry, mathematics and economics. For the purposes of this work, AIs are
machines that can learn, take decision autonomously and interact with the machines that can learn, take decision autonomously and interact with the
environment~\cite{russell_artificial_2021}. environment~\cite{russell_artificial_2021}.
While the possibilities of AI are seemingly endless, the public is slowly but While the possibilities of AI are seemingly endless, the public is slowly but
steadily learning about its limitations. These limitations manifest themselves steadily learning about its limitations. These limitations manifest themselves
in areas such as autonomous driving and medicine, for example. These are fields in areas such as autonomous driving and medicine, for example. These are fields
where AI can have a direct—potentially life-changing—impact on people's lives. A where AI can have a direct—potentially life-changing—impact on people's lives. A
self-driving car operates on roads where accidents can happen at any time. self-driving car operates on roads where accidents can happen at any time.
Decisions made by the car before, during and after the accident can result in Decisions made by the car before, during and after the accident can result in
severe consequences for all participants. In medicine, AIs are increasingly used severe consequences for all participants. In medicine, AIs are increasingly used
to drive human decision-making. The more critical the proper use and functioning to drive human decision-making. The more critical the proper use and functioning
of AI is, the more trust in its architecture and results is required. Trust, of AI is, the more trust in its architecture and results is required. Trust,
however, is not easily defined, especially in relation to artificial however, is not easily defined, especially in relation to artificial
intelligence. intelligence.
This work will explore the following question: \emph{Can artificial intelligence This work will explore the following question: \emph{Can artificial intelligence
be trustworthy, and if so, how?} To be able to discuss this question, trust has be trustworthy, and if so, how?} To be able to discuss this question, trust has
to be defined and dissected into its constituent components. to be defined and dissected into its constituent components.
Chapter~\ref{sec:modeling-trust} analyzes trust and molds the gained insights Chapter~\ref{sec:modeling-trust} analyzes trust and molds the gained insights
into a framework suitable for interactions between humans and artifical into a framework suitable for interactions between humans and artifical
intelligence. Chapter~\ref{sec:taxonomy} approaches trustworthiness in intelligence. Chapter~\ref{sec:taxonomy} approaches trustworthiness in
artificial intelligence from a computing perspective. There are various ways to artificial intelligence from a computing perspective. There are various ways to
make AIs more \emph{trustworthy} through the use of technical means. This make AIs more \emph{trustworthy} through the use of technical means. This
chapter seeks to discuss and summarize important methods and approaches. chapter seeks to discuss and summarize important methods and approaches.
Chapter~\ref{sec:social-computing} discusses combining humans and artificial Chapter~\ref{sec:social-computing} discusses combining humans and artificial
intelligence into one coherent system which is capable of achieving more than intelligence into one coherent system which is capable of achieving more than
either of its parts on their own. either of its parts on their own.
\section{Trust} \section{Trust}
\label{sec:modeling-trust} \label{sec:modeling-trust}
In order to be able to define the requirements and goals of \emph{trustworthy In order to be able to define the requirements and goals of \emph{trustworthy
AI}, it is important to know what trust is and how we humans establish trust AI}, it is important to know what trust is and how we humans establish trust
with someone or something. This section therefore defines and explores different with someone or something. This section therefore defines and explores different
forms of trust. forms of trust.
\subsection{Defining Trust} \subsection{Defining Trust}
Commonly, \emph{trusting someone} means to have confidence in another person's Commonly, \emph{trusting someone} means to have confidence in another person's
ability to do certain things. This can mean that we trust someone to speak the ability to do certain things. This can mean that we trust someone to speak the
truth to us or that a person is competently doing the things that we truth to us or that a person is competently doing the things that we
\emph{entrust} them to do. We trust the person delivering the mail that they do \emph{entrust} them to do. We trust the person delivering the mail that they do
so on time and without mail getting lost on the way to our doors. We trust so on time and without mail getting lost on the way to our doors. We trust
people knowledgeable in a certain field such as medicine to be able to advise us people knowledgeable in a certain field such as medicine to be able to advise us
when we need medical advice. Trusting in these contexts means to cede control when we need medical advice. Trusting in these contexts means to cede control
over a particular aspect of our lives to someone else. We do so in expectation over a particular aspect of our lives to someone else. We do so in expectation
that the trustee does not violate our \emph{social agreement} by acting against that the trustee does not violate our \emph{social agreement} by acting against
our interests. Often times we are not able to confirm that the trustee has our interests. Often times we are not able to confirm that the trustee has
indeed done his/her job. Sometimes we will only find out later that what was indeed done his/her job. Sometimes we will only find out later that what was
in fact done did not happen in line with our own interests. Trust is therefore in fact done did not happen in line with our own interests. Trust is therefore
also always a function of time. Previously entrusted people can—depending on also always a function of time. Previously entrusted people can—depending on
their track record—either continue to be trusted or lose trust. their track record—either continue to be trusted or lose trust.
We do not only trust certain people to act on our behalf, we can also place We do not only trust certain people to act on our behalf, we can also place
trust in things rather than people. Every technical device or gadget receives trust in things rather than people. Every technical device or gadget receives
our trust to some extent, because we expect it to do the things we expect it to our trust to some extent, because we expect it to do the things we expect it to
do. This relationship encompasses \emph{dumb} devices such as vacuum cleaners do. This relationship encompasses \emph{dumb} devices such as vacuum cleaners
and refrigerators, as well as seemingly \emph{intelligent} systems such as and refrigerators, as well as seemingly \emph{intelligent} systems such as
algorithms performing medical diagnoses. Artificial intelligence systems belong algorithms performing medical diagnoses. Artificial intelligence systems belong
to the latter category when they are functioning well, but can easily slip into to the latter category when they are functioning well, but can easily slip into
the former in the case of a poorly trained machine learning algorithm that the former in the case of a poorly trained machine learning algorithm that
simply classifies pictures of dogs and cats always as dogs, for example. simply classifies pictures of dogs and cats always as dogs, for example.
\textcite{ferrario_ai_2020} Scholars usually divide trust either into \emph{cognitive} or
\emph{non-cognitive} forms. While cognitive trust involves some sort of rational
\section{Taxonomy for Trustworthy AI} and objective evaluation of the trustee's capabilities, non-cognitive trust
\label{sec:taxonomy} lacks such an evaluation. For instance, if a patient comes to a doctor with a
health problem which resides in the doctor's domain, the patient will place
trust in the doctor because of the doctor's experience, track record and
\section{Social Computing} education. The patient thus consciously decides that he/she would rather trust
\label{sec:social-computing} the doctor to solve the problem and not a friend who does not have any
expertise. Conversely, non-cognitive trust allows humans to place trust in
people they know well, without a need for rational justification, but just
\section{Conclusion} because of their existing relationship.
\label{sec:conclusion}
Due to the different dimensions of trust and its inherent complexity in
\printbibliography different contexts, frameworks for trust are an active field of research. One
such framework—proposed by \textcite{ferrario_ai_2020}—will be discussed in
\end{document} the following sections.
\subsection{Incremental Model of Trust}
The framework by \textcite{ferrario_ai_2020} consists of three types of trust:
simple trust, reflective trust and paradigmatic trust. Their model thus consists
of the triple
\[ T = \langle\text{simple trust}, \text{reflective trust}, \text{paradigmatic
trust}\rangle \]
\noindent and a 5-tuple
\[ \langle X, Y, A, G, C\rangle \]
\noindent where $X$ and $Y$ denote interacting agents and $A$ the action to be
performed by the agent $Y$ to achieve goal $G$. $C$ stands for the context in
which the action takes place.
\subsubsection{Simple Trust}
\section{Taxonomy for Trustworthy AI}
\label{sec:taxonomy}
\section{Social Computing}
\label{sec:social-computing}
\section{Conclusion}
\label{sec:conclusion}
\printbibliography
\end{document}