2024/04/24 by Danial Samadi Vahdati, Tai D. Nguyen, Vahdati, Danial Samadi +5 · 1 voice · 6 citations
Computer Science · #Adversarial Robustness in Machine Learning #Computer Vision and Pattern Recognition (cs.CV) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #cs.CV
paper · pdf · doi:10.48550/arxiv.2404.15955
openalex publication_date 2024/04/24 · arxiv published 2024/04/24 · arxiv updated 2024/04/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent advances in generative AI have led to the development of techniques to generate visually realistic synthetic video. While a number of techniques have been developed to detect AI-generated synthetic images, in this paper we show that synthetic image detectors are unable to detect synthetic videos. We demonstrate that this is because synthetic video generators introduce substantially different traces than those left by image generators. Despite this, we show that synthetic video traces can be learned, and used to perform reliable synthetic video detection or generator source attribution even after H.264 re-compression. Furthermore, we demonstrate that while detecting videos from new generators through zero-shot transferability is challenging, accurate detection of videos from a new generator can be achieved through few-shot learning.