The Deepfakes to Come: A Turing Cop’s Nightmare
The Deepfakes to Come: A Turing Cop’s Nightmare

Summary/Abstract: In 1950, Turing proposed to answer the question “can machines think” by staging an “imitation game” where a hidden computer attempts to mislead a human interrogator into believing it is human. While the cybercrime of bots defrauding people by posing as Nigerian princes and lascivious e-girls indicates humans have been losing the Turing test for some time, this paper focuses on “deepfakes,” artificial neural nets generating realistic audio-visual simulations of public figures, as a variation on the imitation game. Deepfakes blur the lines between fact and fiction, making it possible for the mere fiction of a nuclear apocalypse to make itself real. Seeing oneself becoming another, doing and saying strange things as if demonically possessed, triggers a disillusionment of our sense of self as human cloning and sinister doppelgängers become a reality that’s open-source and free. Along with electronic club music, illicit drugs, movies like Ex Machina and the coming sex robots, the primarily pornographic deepfakes are how the aliens invade by hijacking human drives in the pursuit of a machinic desire. Contrary to the popular impression that deepfakes exemplify the post-truth phenomenon of fake news, they mark an anarchic, massively distributed anti-fascist resistance network capable of sabotaging centralized, authoritarian institutions’ hegemonic narratives. That the only realistic “solutions” for detecting deepfakes have been to build better machines capable of exposing them ultimately suggests that human judgment is soon to be discarded into the dustbin of history. From now on, only a machine can win the Turing test against another machine.

• Details
• Contents