BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.toorcon.net//toorcamp-2020-2019//talk//FWSLPM
BEGIN:VTIMEZONE
TZID:PST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10;UNTIL=20061029T100000Z
TZNAME:PST
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
END:STANDARD
BEGIN:STANDARD
DTSTART:20071104T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:PST
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20060402T110000Z
TZNAME:PDT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20070311T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:PDT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-toorcamp-2020-2019-FWSLPM@talks.toorcon.net
DTSTART;TZID=PST:20220716T140000
DTEND;TZID=PST:20220716T142000
DESCRIPTION:The recent nature publication\, "Dual use of artificial-intelli
 gence-powered drug discovery" demonstrated that a machine learning model d
 esigned to predict toxicity for drug discovery could be co-opted to genera
 te deadly chemical weapon compounds\, including VX gas and novel\, unchara
 cterized toxic chemical substances. It seems likely that there will be man
 y more such dangerous applications of AI systems\, as these systems grow m
 ore powerful. At the same time\, AI systems are likely to be increasingly 
 useful for a wide variety of applications\, including defensive security. 
 Given this tension\, how can the infosec community help develop good norms
  around the security of AI systems? The infosec community has a lot of exp
 erience navigating tradeoffs in vulnerability disclosure norms. Can these 
 lessons be applied to AI systems that might be capable of generating their
  own vulnerabilities\, in both computer systems and biological systems?
DTSTAMP:20260721T224449Z
LOCATION:Prime Dome
SUMMARY:Securing AI systems with dual-use capabilities - Jeffrey Ladish
URL:https://talks.toorcon.net/toorcamp-2020-2019/talk/FWSLPM/
END:VEVENT
END:VCALENDAR