On the Horizon: Interactive and Compositional Deepfakes
Eric Horvitz

TL;DR
This paper discusses emerging challenges of interactive and compositional deepfakes, which pose societal risks by creating highly realistic, manipulative audiovisual content that can distort perceptions of reality.
Contribution
It introduces the concepts of interactive and compositional deepfakes, highlighting their potential threats and the need for mitigation strategies in the evolving landscape of disinformation.
Findings
Interactive deepfakes can impersonate individuals with realistic behaviors.
Compositional deepfakes can craft synthetic histories over time.
These methods threaten to blur the line between fact and fiction.
Abstract
Over a five-year period, computing methods for generating high-fidelity, fictional depictions of people and events moved from exotic demonstrations by computer science research teams into ongoing use as a tool of disinformation. The methods, referred to with the portmanteau of "deepfakes," have been used to create compelling audiovisual content. Here, I share challenges ahead with malevolent uses of two classes of deepfakes that we can expect to come into practice with costly implications for society: interactive and compositional deepfakes. Interactive deepfakes have the capability to impersonate people with realistic interactive behaviors, taking advantage of advances in multimodal interaction. Compositional deepfakes leverage synthetic content in larger disinformation plans that integrate sets of deepfakes over time with observed, expected, and engineered world events to create…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
