paper-with-me

홈 › Papers

Scaling Laws for Deepfake Detection

2025-10-18 · Wenhao Wang, Longqi Cai, Taihong Xiao, Yuxiao Wang, Ming-Hsuan Yang arxiv

This paper presents a systematic study of scaling laws for the deepfake detection task. Specifically, we analyze the model performance against the number of real image domains, deepfake generation methods, and training images. Since no existing dataset meets the scale requirements for this research, we construct ScaleDF, the largest dataset to date in this field, which contains over 5.8 million real images from 51 different datasets (domains) and more than 8.8 million fake images generated by 102 deepfake methods. Using ScaleDF, we observe power-law scaling similar to that shown in large language models (LLMs). Specifically, the average detection error follows a predictable power-law decay as either the number of real domains or the number of deepfake methods increases. This key observation not only allows us to forecast the number of additional real domains or deepfake methods required to reach a target performance, but also inspires us to counter the evolving deepfake technology in a data-centric manner. Beyond this, we examine the role of pre-training and data augmentations in deepfake detection under scaling, as well as the limitations of scaling itself.

📄 PDF Abstract BibTeX arXiv:2510.16320

Code (0)

등록된 구현이 없습니다.

Tasks

DeepFake Detection

Similar Papers 제목 키워드 기반

Undercover Deepfakes: Detecting Fake Segments in Videos

2023-05-11 · Sanjay Saha, Rashindrie Perera, Sachith Seneviratne, Tamasha Malepathirana 외

The recent renaissance in generative models, driven primarily by the advent of diffusion models and iterative improvement in GAN methods, has enabled many creative applications. However, each advancement is also accompan…

DeepFake DetectionFace Swapping

Anomaly Detection and Localization for Speech Deepfakes via Feature Pyramid Matching

2025-03-23 · Emma Coletta, Davide Salvi, Viola Negroni, Daniele Ugo Leonzio 외

The rise of AI-driven generative models has enabled the creation of highly realistic speech deepfakes - synthetic audio signals that can imitate target speakers' voices - raising critical security concerns. Existing meth…

Anomaly DetectionDeepFake DetectionFace Swapping

D^3: Scaling Up Deepfake Detection by Learning from Discrepancy

2025-01-01 · CVPR 2025 1 · Yongqi Yang, Zhihao Qian, Ye Zhu, Olga Russakovsky 외

The boom of Generative AI brings opportunities entangled with risks and concerns. Existing literature emphasizes the generalization capability of deepfake detection on unseen generators, significantly promoting the d…

DeepFake DetectionFace Swapping

D$^3$: Scaling Up Deepfake Detection by Learning from Discrepancy

2024-04-06 · Yongqi Yang, Zhihao Qian, Ye Zhu, Yu Wu

The boom of Generative AI brings opportunities entangled with risks and concerns. In this work, we seek a step toward a universal deepfake detection system with better generalization and robustness, to accommodate the re…

DeepFake DetectionFace Swapping

Similarity Choice and Negative Scaling in Supervised Contrastive Learning for Deepfake Audio Detection

2026-04-28 · Jaskirat Sudan, Hashim Ali, Surya Subramani, Hafiz Malik arxiv

Supervised contrastive learning (SupCon) is widely used to shape representations, but has seen limited targeted study for audio deepfake detection. Existing work typically combines contrastive terms with broader pipeline…

Audio Deepfake DetectionContrastive Learning