BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211207T055414Z
LOCATION:Online
DTSTART;TZID=America/Chicago:20211119T105000
DTEND;TZID=America/Chicago:20211119T111000
UID:submissions.supercomputing.org_SC21_sess338_ws_xloop105@linklings.com
SUMMARY:Adversarial Attacks against AI-Driven Experimental Peptide Design 
 Workflows
DESCRIPTION:Workshop\n\nAdversarial Attacks against AI-Driven Experimental
  Peptide Design Workflows\n\nRamanathan, Jha\n\nArtificial intelligence/ m
 achine learning (AI/ML) techniques are fueling a revolution in how scienti
 fic experiments are designed, implemented and automated. Specifically, inc
 reasing high-bandwidth instruments coupled to new hardware and software sy
 stems can significantly improve the throughput of experimental results, wh
 ile AI/ML techniques can provide insights into novel science and theories 
 that were hitherto inaccessible. Despite recent progress in such "self-dri
 ving labs'', these automated platforms are susceptible to traditional cybe
 r-security attacks. Using a motivating example of an automated approach to
  design antimicrobial peptides (AMP), our position paper seeks to demonstr
 ate how adversarial attacks may affect the execution of such experimental 
 workflows. We highlight important problems in adversarial robustness that 
 may need to be resolved in order to establish a trustworthy and safe AI-dr
 iven AMP synthesis system.\n\nTag: Online Only, Applications, Scientific C
 omputing\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR