Synthetic Realities: Deep Learning for Detecting AudioVisual Fakes
Battista Biggio · Pavel Korshunov · Thomas Mensink · Giorgio Patrini · Arka Sadhu · Delip Rao

Sat Jun 15th 08:30 AM -- 06:00 PM @ 104 C
Event URL: »

With the latest advances of deep generative models, synthesis of images and videos as well as of human voices have achieved impressive realism. In many domains, synthetic media are already difficult to distinguish from real by the human eye and ear. The potential of misuses of these technologies is seldom discussed in academic papers; instead, vocal concerns are rising from media and security organizations as well as from governments. Researchers are starting to experiment on new ways to integrate deep learning with traditional media forensics and security techniques as part of a technological solution. This workshop will bring together experts from the communities of machine learning, computer security and forensics in an attempt to highlight recent work and discuss future effort to address these challenges. Our agenda will alternate contributed papers with invited speakers. The latter will emphasize connections among the interested scientific communities and the standpoint of institutions and media organizations.

09:00 AM Welcome Remarks Giorgio Patrini
09:10 AM Invited Talk by Professor Alexei Efros (UC Berkeley) (Invited Talk) Alexei Efros
09:40 AM Invited Talk by Dr. Matt Turek (DARPA) (Invited Talk) Matt Turek
10:10 AM Contributed Talk: Limits of Deepfake Detection: A Robust Estimation Viewpoint (Oral Presentation)
10:30 AM Poster session 1 and Coffee break (Poster Session)
11:30 AM Invited Talk by Professor Pawel Korus (NYU) Neural Imaging Pipelines - the Scourge or Hope of Forensics? (Invited Talk)
12:00 PM Contributed Talk: We Need No Pixels: Video Manipulation Detection Using Stream Descriptors (Oral Presenation) David G├╝era
12:15 PM Contributed Talk: A Utility-Preserving GAN for Face Obscuration (Oral Presentation) Hanxiang Hao
12:30 PM Lunch Break (Break)
02:00 PM Invited Talk by Professor Luisa Verdoliva (University Federico II Naples) (Invited Talk) Luisa Verdoliva
02:30 PM Contributed Talk: Tampered Speaker Inconsistency Detection with Phonetically Aware Audio-visual Features (Oral Presentation) Pavel Korshunov
02:45 PM Contributed Talk: Measuring the Effectiveness of Voice Conversion on Speaker Identification and Automatic Speech Recognition Systems (Oral Presentation) Gokce Keskin
03:00 PM Poster session 2 and Coffee break (Poster Session)
03:45 PM CVPR19 Media Forensics workshop: a Preview (Invited Talk)
04:15 PM Invited Talk by Tom Van de Weghe (Stanford & VRT) (Invited Talk)
04:45 PM Invited Talk by Aviv Ovadya (Thoughtful Technology Project) (Invited Talk)
05:00 PM Panel Discussion moderated by Delip Rao (Discussion Panel)

Author Information

Battista Biggio (University of Cagliari)
Pavel Korshunov (IDIAP)
Thomas Mensink (University of Amsterdam)
Giorgio Patrini (Deeptrace)
Arka Sadhu (University of Southern California)
Delip Rao (AI Foundation)