Skip to content

Detecting Synthetic Faces by Understanding Real Faces

Photo of ACM Chicago
Hosted By
ACM C. and ACM
Detecting Synthetic Faces by Understanding Real Faces

Details

NOTE:
We are having some Zoom problems currently which we hope to resolve soon.

Summary

The creation of sophisticated fake videos has been largely relegated to Hollywood studios or state actors. Recent advances in deep learning, however, have democratized the creation of sophisticated and compelling fake images, videos, and audios. This synthetically generated media -- so-called deep fakes -- continue to capture the imagination of the computer-graphics and computer-vision communities.

At the same time, the easy access to technology that can create deep fakes of anybody saying anything continues to be of concern because of its power to disrupt democratic elections, commit small to large-scale fraud, fuel disinformation and misinformation campaigns, and create non-consensual pornography.

To contend with this growing threat, in this talk our speaker will describe a diverse set of techniques to detect state-of-the-art deep-fake videos. One set of these techniques are identity-specific, exploiting soft- and hard-biometric cues like dynamic facial motion and static facial appearance. Another set of these techniques are identity-independent, exploiting the dynamics of lip and ear motion.

About our Speaker

Dr. Shruti Agarwal is currently a postdoctoral researcher in the School of Information at the University of California Berkeley (UCB). She received her Ph.D. from the Department of Computer Sciences at UCB under the supervision of Prof. Hany Farid in the field of multimedia forensics.

Shruti previously worked as a software developer in the Adobe Illustrator team at Adobe, India. She received her master’s and bachelor’s degree in Computer Science from the Indian Institute of Technology (IIT) Delhi, India, and Harcourt Butler Technology Institute (HBTI), India. Her primary research interest lies in multimedia forensics, image analysis, machine learning, and computer vision.

Note: You must register with Zoom, registering in Meetup does not give you access to the Zoom meeting. Please see the Zoom link in the Meetup page or here:
https://acm-org.zoom.us/webinar/register/WN_PVxFZywzSLyMozyN-uk5lw

Agenda:
(Times are Central Standard Time)
6:00pm - brief intros
6:05pm - Talk by Shruti Agarwal
6:45pm - Q&A
7:00pm - end

Photo of ACM Chicago group
ACM Chicago
See more events