Designer | Researcher | Strategist
Designer | Researcher | Strategist
Overview:
A research study exploring video-faking algorithms and the defacing of everyday digital identities. “Deepfake” is a phenomenon that is becoming absurdly dicult to distinguish from authentic footage. These fake videos are used to replace people’s faces to create the illusion of having that person's identity. With this technology, the everyday person could manufacture video “proof” as evidence to make any claim put forth.
A research study exploring video-faking algorithms and the defacing of everyday digital identities. The project entailed developing algorithms and methods that can explain how AI systems reach their decisions or predictions, making them more transparent.
“Deepfake” is a phenomenon that is becoming absurdly difficult to distinguish from authentic footage. These fake videos are used to replace people’s faces to create the illusion of having that person's identity. With this
A Generative AutoEncoder is the foundation for creating deepfakes. It is a neural network that is trained to utilize an input image and output an identical image.
Deepfakes mechanism is trained by two parallel AutoEncoders, one for the original face and another for the new face. During this process, each AutoEncoder is trained to only produce images that resemble the originals.
Upon executing the training of both AutoEncoders, the deepfake process begins when the decoders are switched. The output is a reconstructed image of data, but has the same head alignment and expression from the original photograph.
Presentation and communication involved capturing experiential prototypes through visual and verbal demonstration to convey the concept. Included materials that supported the concept through wizard-of-oz, videos, and posters. Produced a high quality video and documentation of the research project.