Grant / January 2020

Identifying Audio-Video Manipulation by Detecting Temporal Anomalies

Inexpensive recording devices, from cellphones to surveillance cameras, have made audiovisual data ubiquitous, while commercially-available software has made it significantly easier for people to manipulate/alter this data. It has become increasingly important to develop tools for verifying the authenticity of audiovisual data. This research will explore a new method, based on deep neural networks, for detecting fake or manipulated videos. The method will work by identifying situations in which the audio and visual streams of a video are misaligned, a common result of video manipulation.