BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:PDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261101T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:PST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T182857Z
UID:F90E2AD0-CAFE-40A8-8F11-AE0DEA36A3AE
DTSTART;TZID=America/Los_Angeles:20260828T150000
DTEND;TZID=America/Los_Angeles:20260828T160000
DESCRIPTION:Join us for the AI Supply Chain Attacks session to explore how 
 vulnerabilities across the AI lifecycle can compromise models\, datasets\,
  development environments\, CI/CD pipelines\, and deployed AI systems. The
  session will examine how attackers exploit vulnerable third-party package
 s\, poisoned datasets\, compromised pre-trained models\, transfer-learning
  processes\, public model repositories\, and insecure build and deployment
  pipelines. Participants will learn about common attack techniques\, inclu
 ding data and model poisoning\, hidden backdoors\, dependency confusion\, 
 model tampering\, and malicious code embedded within model files.\n\nThe s
 ession will include a case study demonstrating how a compromised AI compon
 ent can move through a CI/CD pipeline and reach production. It will also i
 ntroduce practical defense strategies\, including vulnerability and model 
 scanning\, trusted private repositories\, integrity verification\, model a
 nd data provenance\, governance and lineage\, AI/ML Bills of Materials\, c
 ontinuous monitoring\, and secure MLOps workflows.\n\nAgenda: \nSession ou
 tline\n\n- Fundamentals of AI supply chain risks and attacks targeting dep
 endencies\, models\, datasets\, and CI/CD pipelines\n- Case study covering
  data or model poisoning\, backdoors\, model tampering\, and propagation i
 nto production\n- Defense strategies using scanning\, verification\, prove
 nance\, governance\, AI/ML Bills of Materials\, and secure MLOps\n\nVirtua
 l: https://events.vtools.ieee.org/m/572672
LOCATION:Virtual: https://events.vtools.ieee.org/m/572672
ORGANIZER:badruddoja@csus.edu
SEQUENCE:22
SUMMARY:AI Supply Chain Attacks
URL;VALUE=URI:https://events.vtools.ieee.org/m/572672
X-ALT-DESC:Description: &lt;br /&gt;&lt;p class=&quot;PDq2pG_selectionAnchorContainer&quot; da
 ta-start=&quot;0&quot; data-end=&quot;632&quot;&gt;Join us for the AI Supply Chain Attacks sessio
 n to explore how vulnerabilities across the AI lifecycle can compromise mo
 dels\, datasets\, development environments\, CI/CD pipelines\, and deploye
 d AI systems. The session will examine how attackers exploit vulnerable th
 ird-party packages\, poisoned datasets\, compromised pre-trained models\, 
 transfer-learning processes\, public model repositories\, and insecure bui
 ld and deployment pipelines. Participants will learn about common attack t
 echniques\, including data and model poisoning\, hidden backdoors\, depend
 ency confusion\, model tampering\, and malicious code embedded within mode
 l files.&lt;/p&gt;\n&lt;p data-start=&quot;634&quot; data-end=&quot;1051&quot;&gt;The session will include
  a case study demonstrating how a compromised AI component can move throug
 h a CI/CD pipeline and reach production. It will also introduce practical 
 defense strategies\, including vulnerability and model scanning\, trusted 
 private repositories\, integrity verification\, model and data provenance\
 , governance and lineage\, AI/ML Bills of Materials\, continuous monitorin
 g\, and secure MLOps workflows.&lt;/p&gt;&lt;br /&gt;&lt;br /&gt;Agenda: &lt;br /&gt;&lt;p dir=&quot;auto&quot;
 &gt;Session outline&lt;/p&gt;\n&lt;p&gt;&amp;nbsp\;&lt;/p&gt;\n&lt;div&gt;\n&lt;ul&gt;\n&lt;li data-section-id=&quot;b7
 lbma&quot; data-start=&quot;1062&quot; data-end=&quot;1177&quot;&gt;Fundamentals of AI supply chain ri
 sks and attacks targeting dependencies\, models\, datasets\, and CI/CD pip
 elines&lt;/li&gt;\n&lt;li data-section-id=&quot;14ryb7c&quot; data-start=&quot;1178&quot; data-end=&quot;128
 6&quot;&gt;Case study covering data or model poisoning\, backdoors\, model tamperi
 ng\, and propagation into production&lt;/li&gt;\n&lt;li data-section-id=&quot;1euho10&quot; d
 ata-start=&quot;1287&quot; data-end=&quot;1404&quot; data-is-last-node=&quot;&quot;&gt;Defense strategies u
 sing scanning\, verification\, provenance\, governance\, AI/ML Bills of Ma
 terials\, and secure MLOps&lt;/li&gt;\n&lt;/ul&gt;\n&lt;p&gt;&amp;nbsp\;&lt;/p&gt;\n&lt;/div&gt;
END:VEVENT
END:VCALENDAR