BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.3.7.4//EN
TZID:Asia/Kolkata
X-WR-TIMEZONE:Asia/Kolkata
BEGIN:VEVENT
UID:209@cds.iisc.ac.in
DTSTART;TZID=Asia/Kolkata:20260706T110000
DTEND;TZID=Asia/Kolkata:20260706T120000
DTSTAMP:20260703T060001Z
URL:https://cds.iisc.ac.in/events/cds-kiac-seminar-cds-102-06th-july-towar
 ds-trustworthy-generative-ai/
SUMMARY:CDS-KIAC {Seminar} @ CDS: #102: 06th\, July "Towards Trustworthy Ge
 nerative AI"
DESCRIPTION:We welcome you to CDS-KIAC talk on 06th July 2026 (Monday). The
  details are as below:\n\n\n\nSpeaker : Prof. Karthik Nandakumar\, Associa
 te Professor\, Michigan State University (MSU)\nTitle : Towards Trustworth
 y Generative AI\nDate and Time : July 06\, 2026: 11:00 AM\nVenue : # 102\,
  CDS Seminar Hall\n\n\n\nABSTRACT:\nWhile generative AI models have revolu
 tionized many domains including computer vision and natural language proce
 ssing\, they have introduced new dangers to society. In this talk\, we wil
 l first review the trust issues in generative AI and identify key unsolved
  challenges. Next\, we focus on three specific problems in generative comp
 uter vision and discuss potential solutions. Firstly\, powerful capabiliti
 es of these models can be misused to cause privacy harm to individuals. To
  address this problem\, we show how the inherent vulnerabilities of these 
 models can be leveraged to protect against misuse of facial data. Secondly
 \, we need to ensure the content generated by these models is safe and ali
 gned with human values. In this context\, we demonstrate how models can ro
 bustly unlearn toxic information that has already been imbibed during pre-
 training. Finally\, we now live in a world where we can no longer believe 
 what we see (hear or read)\, especially in digital form. Distinguishing be
 tween natural and synthetically generated or modified image/video content 
 (e.g.\, deepfakes) is one of the grand cybersecurity challenges of the nea
 r future. To solve this problem\, we consider both proactive approaches th
 at watermark all content generated by honest actors and reactive technique
 s like generalizable multimedia forensic detectors that identify content g
 enerated/modified by malicious adversaries. We will conclude with an immed
 iate call for action to make generative AI models trustworthy\, before the
 y begin to cause irreparable real-world harm\n\nBIOGRAPHY:\nKarthik Nandak
 umar is an Associate Professor in the Department of Computer Science and E
 ngineering at Michigan State University (MSU) and an Affiliated Associate 
 Professor in the Computer Vision department at Mohamed bin Zayed Universit
 y of Artificial Intelligence (MBZUAI). Earlier\, he was a Research Staff M
 ember at IBM Research – Singapore and a Scientist at Institute for Infoc
 omm Research\, A*STAR\, Singapore. His primary research interests include 
 trustworthy machine learning\, computer vision\, biometric recognition\, a
 nd applied cryptography. He was a Senior Area Editor of IEEE Transactions 
 on Information Forensics and Security (T-IFS) (2019-23) and a Distinguishe
 d Industry Speaker for the IEEE Signal Processing Society (2020-21)\n\nHos
 t Faculty: Prof. Venkatesh Babu\, CDS\n\n\n\nALL ARE WELCOME
CATEGORIES:Events,Talks
END:VEVENT
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
X-LIC-LOCATION:Asia/Kolkata
BEGIN:STANDARD
DTSTART:20250706T110000
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
TZNAME:IST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR