BEGIN:VCALENDAR PRODID:-//Grails iCalendar plugin//NONSGML Grails iCalendar plugin//EN VERSION:2.0 CALSCALE:GREGORIAN METHOD:PUBLISH BEGIN:VEVENT DTSTAMP:20260417T101200Z DTSTART;TZID=Europe/Berlin:20241031T000000 DTEND;TZID=Europe/Berlin:20241031T000000 SUMMARY:Is AI Deception Deception UID:20260418T091547Z-iCalPlugin-Grails@philevents-web-f5d4878dd-g4ggw TZID:Europe/Berlin LOCATION:Lindholmen Conference Centre\, Gothenburg\, Sweden\, 417 56 DESCRIPTION:

The visual and literary arts are rife with narratives of AI systems &lsquo\;manipulating&rsquo\; humans or &lsquo\;lying&rsquo\; to them to further their own aims. Some recent academic studies also seem to indicate that AI systems can induce non-ideal mental states (e.g.\, false beliefs) in their users \;in pursuing certain objectives e.g.\, winning a game (Diplomacy)\, or performing tasks that are out of their reach (solving a \;captcha).

\n

This workshop will focus on the topic of deception by artificial systems and address some of the following questions: \;In what ways can AI systems be deceptive? How bad is it that we have chosen to have \;AI systems behave in an anthromorphic manner? Can AI systems deceive humans just as humans can deceive each other? Do the capacities which make AI systems useful also make them deceptive? What is the significance of deception by AI systems for our societies? How can we address the challenges posed by AI Deception?

\n

Confirmed invited speakers at the workshop include:

\n
    \n
  1. Dimitri Coelho Mollo \;(Umeå\; University)
    2. \n
  2. Jessica Pepp \;(Uppsala University) \;
    3. \n
  3. OndÅ™ej Krá\;sa (University of Pardubice)
    4. \n
  4. Rachel Sterken \;(University of Hong Kong)
    5. \n
\n

The entire workshop is 3 hours long (9:00 - 12:00 Hrs) and is divided into two sessions (of approx. 80 minutes each\, including Q&\;A). There will be a \;fika \;break in the middle. Participants will also have an opportunity to present their work (on the conceptual or practical issues related to deception by AI systems) through lightning talks. If you would like to present\, please mention this in your registration email.

\n

Preparation for participants

\n

Participants are expected to read short descriptions of the talks (and panel discussions) before the workshop. Suggested readings will be posted two weeks before the date of the workshop.

\n

Registration information

\n

Please first register for the \;main conference\, then send an email (with subject &lsquo\;AI Deception Workshop&rsquo\;) to \;nikhil.mahant@filosofi.uu.se \;expressing your interest. Please also include a link to your webpage\, academic profile\, or CV. Applications will be evaluated on a rolling basis\, but the deadline to register is 1 November\, 2024.

\n

(A limited number of travel or stay sponsorships are available for participants who are giving lightning talks and whose research profile is particularly suited to the workshop\, but who do not have any sources of funding available to them. If you would like to be considered\, please register before 1 November and mention this in your registration email.)

\n

For any questions\, please email the host: nikhil.mahant@filosofi.uu.se

ORGANIZER;CN=Nikhil Mahant: METHOD:PUBLISH END:VEVENT END:VCALENDAR