Report Open Access

Fail-Safe Execution of Deep Learning based Systems through Uncertainty Monitoring

Michael Weiss; Paolo Tonella

MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="">
  <controlfield tag="005">20210702014817.0</controlfield>
  <controlfield tag="001">5055710</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Università della Svizzera italiana</subfield>
    <subfield code="a">Paolo Tonella</subfield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">903143</subfield>
    <subfield code="z">md5:ed486374270224a43e2ebc6cf3cd2a5e</subfield>
    <subfield code="u"></subfield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2020-09-01</subfield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="o"></subfield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Università della Svizzera italiana</subfield>
    <subfield code="a">Michael Weiss</subfield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Fail-Safe Execution of Deep Learning based Systems through Uncertainty Monitoring</subfield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">787703</subfield>
    <subfield code="a">Self-assessment Oracles for Anticipatory Testing</subfield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u"></subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2"></subfield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;Modern software systems rely on Deep Neural Networks (DNN) when processing complex, unstructured inputs, such as images, videos, natural language texts or audio signals.&amp;nbsp;Provided the intractably large size of such input spaces, the intrinsic limitations of learning algorithms&amp;nbsp; and the ambiguity about the expected predictions for some of the inputs, not only there is no guarantee that DNN&amp;#39;s predictions are always correct, but rather developers must safely assume a low, though not negligible, error probability.&amp;nbsp;A fail-safe Deep Learning based System (DLS) is one equipped to handle DNN faults by means of a supervisor, capable of recognizing predictions that should not be trusted and that should activate a healing procedure bringing the DLS to a safe state.&lt;/p&gt;

&lt;p&gt;In this paper, we propose an approach to use DNN uncertainty estimators to implement such supervisor.&amp;nbsp;We first discuss advantages and disadvantages of existing approaches to measure uncertainty for DNNs&amp;nbsp;and propose novel metrics for the empirical assessment of the&amp;nbsp; supervisor that rely on such approaches.&amp;nbsp;We then describe our publicly available tool Uncertainty-Wizard, which allows transparent estimation of uncertainty for regular tf.keras DNNs.&amp;nbsp;Lastly, we discuss a large-scale&amp;nbsp; study conducted on four different subjects to empirically validate the approach,&amp;nbsp;reporting the lessons-learned as guidance for software engineers who intend to monitor uncertainty for fail-safe execution of DLS.&lt;/p&gt;</subfield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isObsoletedBy</subfield>
    <subfield code="a">10.1109/ICST49551.2021.00015</subfield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.5055709</subfield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.5055710</subfield>
    <subfield code="2">doi</subfield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">report</subfield>
All versions This version
Views 2727
Downloads 2828
Data volume 25.3 MB25.3 MB
Unique views 2323
Unique downloads 2525


Cite as