BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20240310T030000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:PDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241103T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:PST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241018T060921Z
UID:A38D7657-9F1B-4903-B9B3-E8FD43901F38
DTSTART;TZID=America/Los_Angeles:20241017T170000
DTEND;TZID=America/Los_Angeles:20241017T183000
DESCRIPTION:This talk explores the intersection of image processing and com
 puter vision with crucial forensics and privacy challenges\, shedding ligh
 t on innovative methods and inherent vulnerabilities. We begin by examinin
 g the potential of consumer-grade cameras for capturing detailed 3D surfac
 e structures at a microscopic level\, enabling extracting the "fingerprint
 " information for the high-accuracy\, low-cost authentication of important
  documents and product packaging. Building on the theme of information ext
 raction\, we delve into how indoor camera images can inadvertently reveal 
 location information\, offering a powerful tool for the potential capture 
 of child exploiters. Finally\, we transition to analyze the vulnerabilitie
 s within federated learning systems. We demonstrate how training images ca
 n be silently extracted by a curious but honest server or from participati
 ng clients\, raising significant concerns about data privacy for the poten
 tial deployment of federated learning systems.\n\nSpeaker(s): Chau-Wei Won
 g\, \n\nVirtual: https://events.vtools.ieee.org/m/437937
LOCATION:Virtual: https://events.vtools.ieee.org/m/437937
ORGANIZER:pzh@ieee.org
SEQUENCE:17
SUMMARY:IEEE SPS SCV - Leveraging Image Processing for Forensics and Privac
 y in the Digital Age
URL;VALUE=URI:https://events.vtools.ieee.org/m/437937
X-ALT-DESC:Description: <br /><p class="p1">This talk explores the intersec
 tion of image processing and computer vision with crucial forensics and pr
 ivacy challenges\, shedding light on innovative methods and inherent vulne
 rabilities. We begin by examining the potential of consumer-grade cameras 
 for capturing detailed 3D surface structures at a microscopic level\, enab
 ling extracting the "fingerprint" information for the high-accuracy\, low-
 cost authentication of important documents and product packaging. Building
  on the theme of information extraction\, we delve into how indoor camera 
 images can inadvertently reveal location information\, offering a powerful
  tool for the potential capture of child exploiters. Finally\, we transiti
 on to analyze the vulnerabilities within federated learning systems. We de
 monstrate how training images can be silently extracted by a curious but h
 onest server or from participating clients\, raising significant concerns 
 about data privacy for the potential deployment of federated learning syst
 ems.</p>
END:VEVENT
END:VCALENDAR