<div dir="ltr">
<span style="color:rgb(33,33,33);font-size:13.32px;font-family:wf_segoe-ui_normal,Segoe UI,Segoe WP,Tahoma,Arial,sans-serif,serif,EmojiFont"><table><tbody><tr><td><div><b><span style="font-size:16pt">DeceptECAI2020: International Workshop on Deceptive AI @ECAI2020</span></b></div>
<div><span style="font-size:12pt">University of Santiago de Compostela</span></div>
<div><span style="font-size:12pt">Santiago de Compostela, Spain, August 29-30, 2020</span></div>
</td>
</tr>
</tbody></table>
<table>
<tbody><tr>
<td><span style="font-size:12pt">Conference website</span></td>
<td><a href="https://sites.google.com/view/deceptecai2020/home" target="_blank" rel="noopener noreferrer"><span style="font-size:12pt">https://sites.google.com/view/deceptecai2020/home</span></a></td>
</tr>
<tr>
<td><span style="font-size:12pt">Submission link</span></td>
<td><a href="https://easychair.org/conferences/?conf=deceptecai2020" target="_blank" rel="noopener noreferrer"><span style="font-size:12pt">https://easychair.org/conferences/?conf=deceptecai2020</span></a></td>
</tr>
<tr>
<td><span style="font-size:12pt">Submission deadline</span></td>
<td><span style="font-size:12pt">May 25, 2020</span></td>
</tr>
<tr>
<td><span style="font-size:12pt">Notification of acceptance</span></td>
<td><span style="font-size:12pt">June 15, 2020</span></td>
</tr>
</tbody></table>
<div><br>

</div>
<div><a href="https://easychair.org/cfp/topic.cgi?tid=7249426;a=23836792" target="_blank" rel="noopener noreferrer"><span><br>

</span></a></div>
<p dir="ltr" style="margin-top:0px;margin-bottom:0px"><span style="color:black;font-size:12pt;font-family:Arial">There
 is no dominant theory of deception. The literature on deception treats 
different aspects and components of deception separately, sometimes 
offering
contradictory evidence and opinions on these components. Emerging AI 
techniques offer an exciting and novel opportunity to expand our 
understanding of deception from a computational perspective. However, 
the design, modelling and engineering of deceptive machines
is not trivial from either conceptual, engineering, scientific, or 
ethical perspectives. The aim of DeceptECAI is to bring together people 
from academia, industry and policy-making in order to discuss and 
disseminate the current and future threats, risks, and
even benefits of designing deceptive AI. The workshop proposes a 
multidisciplinary approach (Computer Science, Psychology, Sociology, 
Philosophy & Ethics, Military Studies, Law etc.) to discuss the 
following aspects of deceptive AI:</span></p>
<p dir="ltr" style="margin-top:0px;margin-bottom:0px"><span style="color:black;font-size:12pt;font-family:Arial"><br>

</span></p>
<p dir="ltr" style="margin-top:0px;margin-bottom:0px"><span style="font-size:12pt"><strong>1) Behaviour</strong></span><span style="color:black;font-size:12pt;font-family:Arial"> - What type of machine behaviour should be considered deceptive? How do we study
deceptive behaviour in machines as opposed to humans?</span></p>
<p dir="ltr" style="margin-top:0px;margin-bottom:0px"><span style="font-size:12pt"><strong>2) Reasoning</strong></span><span style="color:black;font-size:12pt;font-family:Arial"> - What kind of reasoning mechanisms lie behind deceptive behaviour? Also, what
type of reasoning mechanisms are more prone to deception?</span></p>
<p dir="ltr" style="margin-top:0px;margin-bottom:0px"><span style="font-size:12pt"><strong>3) Cognition</strong></span><span style="color:black;font-size:12pt;font-family:Arial"> - How does cognition affect deception and how does deception affect cognition?
Also, what function, if any, do agent cognitive architectures play in deception?</span></p>
<p dir="ltr" style="margin-top:0px;margin-bottom:0px"><span style="font-size:12pt"><strong>4) AI & Society</strong></span><span style="color:black;font-size:12pt;font-family:Arial"> - How does the ability of machines to deceive influence society? What kinds
of measures do we need to take in order to neutralise or mitigate the negative effects of deceptive AI?</span></p>
<p style="margin-top:0px;margin-bottom:0px"><span style="font-size:12pt"><strong>5) Engineering Principles</strong></span><span style="color:black;font-size:12pt;font-family:Arial"> - How should we engineer autonomous agents such that we are able to know why
and when they deceive? Also, why should or shouldn’t we engineer or model deceptive machines?</span></p>
<h2><span style="font-size:12pt">Submission Guidelines</span></h2>
<p style="margin-top:0px;margin-bottom:0px"><span style="font-size:12pt">All papers must be original and not simultaneously submitted to another journal or conference.</span></p>
<p dir="ltr" style="text-align:justify;margin-top:0px;margin-bottom:0px"><span style="color:black;font-size:12pt;font-family:Arial">Submissions are NOT anonymous. The names and affiliations of the authors should be stated in the manuscript.</span></p>
<p style="margin-top:0px;margin-bottom:0px"><span style="color:black;font-size:12pt;font-family:Arial">All papers should be formatted following the Springer</span><a href="https://www.springer.com/gb/computer-science/lncs/conference-proceedings-guidelines" target="_blank" rel="noopener noreferrer"><span style="color:black;font-size:12pt;font-family:Arial">
</span><span style="font-size:12pt"><u>LNCS/LNAI guidelines</u></span></a><span style="color:black;font-size:12pt;font-family:Arial"> and submitted through EasyChair.</span></p>
<p style="margin-top:0px;margin-bottom:0px"><span style="font-size:12pt">The following paper categories are welcome:</span></p>
<ul><span style="font-size:12pt"></span><li><span style="font-size:12pt"><strong>Long papers </strong></span><span style="font-size:12pt"><strong>(12 pages + 1 page references):</strong></span><span style="color:black;font-size:12pt;font-family:Arial"> Long papers should </span><span style="color:black;font-size:12pt;font-family:Arial">present
original research work and be no longer than thirteen pages in </span><span style="color:black;font-size:12pt;font-family:Arial">total: twelve pages for the main text of the paper (including all </span><span style="color:black;font-size:12pt;font-family:Arial">figures
but excluding references), and one additional page for </span><span style="color:black;font-size:12pt;font-family:Arial">references. </span></li><span style="font-size:12pt"></span><li><span style="font-size:12pt"><strong>Short papers </strong></span><span style="font-size:12pt"><strong>(7 pages + 1 page references):</strong></span><span style="color:black;font-size:12pt;font-family:Arial"> Short papers may </span><span style="color:black;font-size:12pt;font-family:Arial">report
on works in progress. Short paper submissions should be no </span><span style="color:black;font-size:12pt;font-family:Arial">longer than eight pages in total: seven pages for the main text of the </span><span style="color:black;font-size:12pt;font-family:Arial">paper
(including all figures but excluding references), and one </span><span style="color:black;font-size:12pt;font-family:Arial">additional page for references. </span></li><span style="font-size:12pt"></span><li><span style="font-size:12pt"><strong>Position papers</strong></span><span style="color:black;font-size:12pt;font-family:Arial"> regarding potential </span><span style="color:black;font-size:12pt;font-family:Arial">research challenges are also welcomed
in either long or short paper </span><span style="color:black;font-size:12pt;font-family:Arial">format.</span></li></ul>
<h2><span style="font-size:12pt">List of Topics</span></h2>
<ul><span style="font-size:12pt"></span><li><span style="font-size:12pt">Deceptive Machines</span></li><span style="font-size:12pt"></span><li><span style="color:black;font-size:12pt;font-family:Arial">Multi-Agent Systems and Agent-Based Models </span></li><span style="font-size:12pt"></span><li><span style="color:black;font-size:12pt;font-family:Arial">Trust and Security in AI</span></li><span style="font-size:12pt"></span><li><span style="color:black;font-size:12pt;font-family:Arial">Machine Behaviour</span></li><span style="font-size:12pt"></span><li><span style="color:black;font-size:12pt;font-family:Arial">Argumentation</span></li><span style="font-size:12pt"></span><li><span style="color:black;font-size:12pt;font-family:Arial">Machine Learning</span></li><span style="font-size:12pt"></span><li><span style="color:black;font-size:12pt;font-family:Arial">Explainable AI - XAI</span></li><span style="font-size:12pt"></span><li><span style="color:black;font-size:12pt;font-family:Arial">Human-Computer(Agent) Interaction - HCI/HAI</span></li><span style="font-size:12pt"></span><li><span style="color:black;font-size:12pt;font-family:Arial">Philosophical, Psychological, and Sociological aspects</span></li><span style="font-size:12pt"></span><li><span style="color:black;font-size:12pt;font-family:Arial">Ethical, Moral, Political, Economical, and Legal aspects</span></li><span style="font-size:12pt"></span><li><span style="color:black;font-size:12pt;font-family:Arial">Storytelling and Narration in AI</span></li><span style="font-size:12pt"></span><li><span style="color:black;font-size:12pt;font-family:Arial">Computational Social Science</span></li><span style="font-size:12pt"></span><li><span style="color:black;font-size:12pt;font-family:Arial">Applications related to deceptive AI<br>

</span></li></ul>
<div><br>

</div>
<h3><span style="font-size:12pt">Organizing committee</span></h3>
<ul><span style="font-size:12pt"></span><li><span style="color:black;font-size:12pt;font-family:Arial">Stefan Sarkadi - King’s College London, UK</span></li><span style="font-size:12pt"></span><li><span style="color:black;font-size:12pt;font-family:Arial">Peter McBurney - King’s College London, UK</span></li><span style="font-size:12pt"></span><li><span style="color:black;font-size:12pt;font-family:Arial">Liz Sonenberg - University of Melbourne, Australia</span></li><span style="font-size:12pt"></span><li><span style="color:black;font-size:12pt;font-family:Arial">Iyad Rahwan - </span><span style="font-size:12pt">Max Planck Institute for Human Development & MIT, Germany & USA</span></li></ul>
<h2><span style="font-size:12pt">Publication</span></h2>
<p style="margin-top:0px;margin-bottom:0px"><span style="font-size:12pt">DeceptECAI2020 proceedings will be published in</span><span style="color:black;font-size:12pt;font-family:Arial"> Springer CCIS. We are also planning a Special Issue on the topic of "Deceptive
AI" in a highly-ranked Journal.</span></p>
<h2><span style="font-size:12pt">Contact</span></h2>
<p style="margin-top:0px;margin-bottom:0px"><span style="font-size:12pt">All questions about submissions should be emailed to </span><span style="color:black;font-size:12pt;font-family:Arial"><a href="mailto:stefan.sarkadi@kcl.ac.uk">stefan.sarkadi@kcl.ac.uk</a></span></p></span>

</div>