# On the Horizon: Interactive and Compositional Deepfakes

arXiv: https://arxiv.org/abs/2209.01714 · HTML: https://mlsanity.com/paper/2209.01714/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 50 references that are in the map.
- First posted on arXiv 5 Sep 2022.

## Builds on (most cited first, 9 of 9)

- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Face2Face: Real-time Face Capture and Reenactment of RGB Videos](https://mlsanity.com/paper/2007.14808/) (2020)
- [Neural Voice Puppetry: Audio-driven Facial Reenactment](https://mlsanity.com/paper/1912.05566/) (2019)
- [Neural Voice Cloning with a Few Samples](https://mlsanity.com/paper/1802.06006/) (2018)
- [Deep Voice: Real-time Neural Text-to-Speech](https://mlsanity.com/paper/1702.07825/) (2017)
- [Event2Mind: Commonsense Inference on Events, Intents, and Reactions](https://mlsanity.com/paper/1805.06939/) (2018)
- [Contrastive Explanations with Local Foil Trees](https://mlsanity.com/paper/1806.07470/) (2018)
- [AMP: Authentication of Media via Provenance](https://mlsanity.com/paper/2001.07886/) (2020)
- [Imagined versus Remembered Stories: Quantifying Differences in Narrative Flow](https://mlsanity.com/paper/2201.02662/) (2022)

## Built on by (most cited first, 13 of 13)

- [Frontier AI Regulation: Managing Emerging Risks to Public Safety](https://mlsanity.com/paper/2307.03718/) (2023)
- [Red-Teaming for Generative AI: Silver Bullet or Security Theater?](https://mlsanity.com/paper/2401.15897/) (2024)
- [A Comprehensive Review of Data-Driven Co-Speech Gesture Generation](https://mlsanity.com/paper/2301.05339/) (2023)
- [Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives](https://mlsanity.com/paper/2311.09227/) (2023)
- [Protecting Society from AI Misuse: When are Restrictions on Capabilities Warranted?](https://mlsanity.com/paper/2303.09377/) (2023)
- [Exploring the Relevance of Data Privacy-Enhancing Technologies for AI Governance Use Cases](https://mlsanity.com/paper/2303.08956/) (2023)
- [Deepfakes and Higher Education: A Research Agenda and Scoping Review of Synthetic Media](https://mlsanity.com/paper/2404.15601/) (2024)
- [Principles of Designing Robust Remote Face Anti-Spoofing Systems](https://mlsanity.com/paper/2406.03684/) (2024)
- [Contextual Confidence and Generative AI](https://mlsanity.com/paper/2311.01193/) (2023)
- [AI Horizon Scanning, White Paper p3395, IEEE-SA. Part I: Areas of Attention](https://mlsanity.com/paper/2410.01808/) (2024)
- [Automatic Authorities: Power and AI](https://mlsanity.com/paper/2404.05990/) (2024)
- [A Human-Centered Approach to Identifying Promises, Risks, & Challenges of Text-to-Image Generative AI in Radiology](https://mlsanity.com/paper/2507.16207/) (2025)
- [Generative Propaganda](https://mlsanity.com/paper/2509.19147/) (2025)

## Abstract (arXiv)

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 persuasive synthetic histories. Synthetic histories can be constructed manually but may one day be guided by adversarial generative explanation (AGE) techniques. In the absence of mitigations, interactive and compositional deepfakes threaten to move us closer to a post-epistemic world, where fact cannot be distinguished from fiction. I shall describe interactive and compositional deepfakes and reflect about cautions and potential mitigations to defend against them.