BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261101T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260519T112118Z
UID:7AE0018C-BB23-4D68-9CB3-E096DB3C234B
DTSTART;TZID=America/New_York:20260518T174500
DTEND;TZID=America/New_York:20260518T184700
DESCRIPTION:[]\n\nLarge language models (LLMs) and Generative AI (GenAI) ar
 e at the forefront of frontier AI research and technology. With their rapi
 dly increasing popularity and availability\, challenges and concerns about
  their misuse and safety risks are becoming more prominent than ever. In t
 his talk\, we introduce a unified computational framework for evaluating a
 nd improving a wide range of safety challenges in generative AI. Specifica
 lly\, we will show new tools and insights to explore and mitigate the safe
 ty and robustness risks associated with state-of-the-art LLMs and GenAI mo
 dels\, including (i) safety risks in fine-tuning LLMs\, (ii) LLM red-teami
 ng and jailbreak mitigation\, (iii) prompt engineering for safety debuggin
 g\, and (iv) robust detection of AI-generated content.\n\nWhere: Webinar (
 Join link will be provided after registration)\nPDHs: One Hour (Issued ONL
 Y by prior email request)\n\nSpeaker(s): Pin-Yu Chen\, \n\nAgenda: \n545 p
 m start\n\n645 pm end\n\nVirtual: https://events.vtools.ieee.org/m/559586
LOCATION:Virtual: https://events.vtools.ieee.org/m/559586
ORGANIZER:sharan.kalwani@ieee.org
SEQUENCE:27
SUMMARY:Computational Safety for Generative AI
URL;VALUE=URI:https://events.vtools.ieee.org/m/559586
X-ALT-DESC:Description: &lt;br /&gt;&lt;p&gt;&lt;img style=&quot;border-width: 20px\; border-st
 yle: hidden\; float: left\; margin: 20px\;&quot; src=&quot;https://events.vtools.iee
 e.org/vtools_ui/media/display/b1c8a4a5-f6df-4173-a011-6e655cdc508b&quot; alt=&quot;&quot;
  width=&quot;262&quot; height=&quot;284&quot;&gt;&lt;/p&gt;\n&lt;div&gt;\n&lt;p&gt;Large language models (LLMs) and
  Generative AI (GenAI) are at the forefront of frontier AI research and te
 chnology. With their rapidly increasing popularity and availability\, chal
 lenges and concerns about their misuse and safety risks are becoming more 
 prominent than ever. In this talk\, we introduce a unified computational f
 ramework for evaluating and improving a wide range of safety challenges in
  generative AI. Specifically\, we will show new tools and insights to expl
 ore and mitigate the safety and robustness risks associated with state-of-
 the-art LLMs and GenAI models\, including (i) safety risks in fine-tuning 
 LLMs\, (ii) LLM red-teaming and jailbreak mitigation\, (iii) prompt engine
 ering for safety debugging\, and (iv) robust detection of AI-generated con
 tent.&lt;/p&gt;\n&lt;/div&gt;\n&lt;div&gt;&amp;nbsp\;&lt;/div&gt;\n&lt;p&gt;Where: Webinar (Join link will b
 e provided after registration)&lt;br&gt;PDHs: One Hour (Issued ONLY by prior ema
 il request)&lt;/p&gt;&lt;br /&gt;&lt;br /&gt;Agenda: &lt;br /&gt;&lt;p&gt;545 pm start&lt;/p&gt;\n&lt;p&gt;645 pm en
 d&lt;/p&gt;\n&lt;p&gt;&amp;nbsp\;&lt;/p&gt;
END:VEVENT
END:VCALENDAR