The Deep of Deepfakes refers to Deep Learning, and the fake refers to the function of the software - to take a real video of a human being and digitally alter their face to match someone else's face. Here are two examples:

This software produces curiously convincing fake videos. Yet, there's something slightly off about them. Surely machine learning can be used to determine real from fake... right? Siwei Lyu and his collaborators certainly thought so and demonstrated this idea by identifying a novel, detectable feature which was commonly missing from videos produced by the Deep Fakes software.

In this episode, we discuss this use case for deep learning, detecting fake videos, and the threat of fake videos in the future.

" /> Deep Fakes

The Deep of Deepfakes refers to Deep Learning, and the fake refers to the function of the software - to take a real video of a human being and digitally alter their face to match someone else's face. Here are two examples:

This software produces curiously convincing fake videos. Yet, there's something slightly off about them. Surely machine learning can be used to determine real from fake... right? Siwei Lyu and his collaborators certainly thought so and demonstrated this idea by identifying a novel, detectable feature which was commonly missing from videos produced by the Deep Fakes software.

In this episode, we discuss this use case for deep learning, detecting fake videos, and the threat of fake videos in the future.

" />

The Deep of Deepfakes refers to Deep Learning, and the fake refers to the function of the software - to take a real video of a human being and digitally alter their face to match someone else's face. Here are two examples:

This software produces curiously convincing fake videos. Yet, there's something slightly off about them. Surely machine learning can be used to determine real from fake... right? Siwei Lyu and his collaborators certainly thought so and demonstrated this idea by identifying a novel, detectable feature which was commonly missing from videos produced by the Deep Fakes software.

In this episode, we discuss this use case for deep learning, detecting fake videos, and the threat of fake videos in the future.

" />

Deep Fakes

<p>Digital videos can be described as sequences of still images and associated audio. Audio is easy to fake. What about video?</p> <p>A video can easily be broken down into a sequence of still images replayed rapidly in sequence. In this context, videos are simply very high dimensional sequences of observations, ripe for input into a machine learning algorithm.</p> <p>The availability of commodity hardware, clever algorithms, and well-designed software to implement those algorithms at scale make it possible to do machine learning on video, but to what end? There are many answers, one interesting approach being the technology called "DeepFakes".</p> <p>The Deep of Deepfakes refers to Deep Learning, and the fake refers to the function of the software - to take a real video of a human being and digitally alter their face to match someone else's face. Here are two examples:</p> <ul> <li> <p><a href="https://www.youtube.com/watch?v=cQ54GDm1eL0">Barack Obama via Jordan Peele</a></p> </li> <li> <p><a href="https://www.youtube.com/watch?v=BU9YAHigNx8">The versatility of Nick Cage</a></p> </li> </ul> <p>This software produces curiously convincing fake videos. Yet, there's something slightly off about them. Surely machine learning can be used to determine real from fake... right? Siwei Lyu and his collaborators certainly thought so and demonstrated this idea by identifying a novel, detectable feature which was commonly missing from videos produced by the Deep Fakes software.</p> <p>In this episode, we discuss this use case for deep learning, detecting fake videos, and the threat of fake videos in the future.</p>

Guest

Siwei Lyu: Siwei Lyu is a SUNY Distinguished Professor and a SUNY Empire Innovation Professor at the Department of Computer Science and Engineering, the Director of the UB Media Forensic Lab (UB MDFL), and the founding Co-Director of the Center for Information Integrity (CII) at the University at Buffalo, State University of New York, USA. Before joining UB, Dr. Lyu served as an Assistant Professor (2008-2014), tenured Associate Professor (2014-2019), and Full Professor (2019-2020) at the Department of Computer Science at the University at Albany, State University of New York. He is the Founding Director of UAlbany's Computer Vision and Machine Learning Lab (CVML). From 2005 to 2008, he worked as a Post-Doctoral Research Associate at the Howard Hughes Medical Institute and the Center for Neural Science at New York University. In 2001, he was an Assistant Researcher at Microsoft Research Asia. Dr. Lyu earned his Ph.D. in Computer Science from Dartmouth College in 2005 and both his M.S. (2000) and B.S. (1997) degrees in Computer Science and Information Science, respectively, from Peking University, China. Dr. Lyu's research interests include media forensics, computer vision, and machine learning. He has published over 240 refereed journal and conference papers. His research projects are funded by NSF, DARPA, and the US Department of Homeland Security. Dr. Lyu has received numerous awards, such as the IEEE Signal Processing Society Best Paper Award (2011), the National Science Foundation CAREER Award (2010), SUNY Albany's Presidential Award for Excellence in Research and Creative Activities (2017), SUNY Chancellor's Award for Excellence in Research and Creative Activities (2018), Google Faculty Research Award (2019), and IEEE Region 1 Technological Innovation (Academic) Award (2021). Dr. Lyu has served on the IEEE Signal Processing Society's Information Forensics and Security Technical Committee and held editorial positions with several prestigious journals. Dr. Lyu holds prestigious memberships and distinctions, including being a Fellow of IEEE, IAPR, and AAIA. He is also a Distinguished Member of ACM, a Senior Member of the Sigma Xi Society, and a Member of the Omicron Delta Kappa society.

Deep Fakes