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

Change formatting of simple trust

Browse Source
This commit is contained in:
Tobias Eidelpes 2021-12-14 15:55:56 +01:00
parent 6d0fdc038b
commit c6b2bd0d88
1 changed files with 27 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
trustworthy-ai.tex
View File

@ -141,20 +141,34 @@ of the triple
performed by the agent $Y$ to achieve goal $G$. $C$ stands for the context in performed by the agent $Y$ to achieve goal $G$. $C$ stands for the context in
which the action takes place. which the action takes place.
\subsubsection{Simple Trust} \subsubsection{Simple Trust} is a non-cognitive form of trust and the least
demanding form of trust in the incremental model. $X$ trusts $Y$ to perform an
action $A$ to pursue the goal $G$ without requiring additional information about
$Y$'s ability to generate a satisfactory outcome. In other words, $X$
\emph{depends} on $Y$ to perform an action. $X$ has no control over the process
and also does not want to control it or the outcome. A lot of day-to-day
interactions happen in some form or another under simple trust: we (simply)
trust a stranger on the street to show us the right way when we are lost.
Sometimes simple trust is unavoidable because of the trustor's inability to
obtain additional information about the other party. Children, for example, have
to simply trust adults not because they want to but out of necessity. This
changes when they get older and develop their ability to better judge other
people.
is a non-cognitive form of trust and the least demanding form of trust in the \subsubsection{Reflective Trust} adds an additional layer to the simple trust
incremental model. $X$ trusts $Y$ to perform an action $A$ to pursue the goal model: trustworthiness. Trustworthiness can be defined as the cognitive belief
$G$ without requiring additional information about $Y$'s ability to generate a of $X$ that $Y$ is trustworthy. Reflective trust involves a cognitive process
satisfactory outcome. In other words, $X$ \emph{depends} on $Y$ to perform an which allows a trustor to obtain reasons for trusting a potential trustee. $X$
action. $X$ has no control over the process and also does not want to control it believes in the trustworthiness of $Y$ because there are reasons for $Y$ being
or the outcome. A lot of day-to-day interactions happen in some form or another trustworthy. Similarly to simple trust, reflective trust is still missing the
under simple trust: we (simply) trust a stranger on the street to show us the aspect of control. Reflective trust does not have to be expressed in binary
right way when we are lost. Sometimes simple trust is unavoidable because of the form but can also be expressed by a subjective measure of confidence. The more
trustor's inability to obtain additional information about the other party. likely a trustee $Y$ is to perform action $A$ towards a goal $G$, the higher
Children, for example, have to simply trust adults not because they want to but $X$'s confidence in $Y$ is. Additionally, $X$ might have high reflective trust
out of necessity. This changes when they get older and develop their ability to in $Y$ but still does not trust $Y$ to perform a given task because of other,
better judge other people. potentially unconscious, reasons.
\subsubsection{Pragmatic Trust}
\section{Taxonomy for Trustworthy AI} \section{Taxonomy for Trustworthy AI}
\label{sec:taxonomy} \label{sec:taxonomy}