Beyond Deepfake Images: Detecting AI-Generated Videos
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Few-Shot Learning by Explicit Physics Integration: An Application to Groundwater Heat Transport
Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detection
Post-training for Deepfake Speech Detection
Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks
Universal Music Representations? Evaluating Foundation Models on World Music Corpora
FAME: A Lightweight Spatio-Temporal Network for Model Attribution of Face-Swap Deepfakes
토론
이 논문과 연결된 포럼 글이 아직 없습니다.