all AI news
D$^3$: Scaling Up Deepfake Detection by Learning from Discrepancy
April 9, 2024, 4:46 a.m. | Yongqi Yang, Zhihao Qian, Ye Zhu, Yu Wu
cs.CV updates on arXiv.org arxiv.org
Abstract: 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 responsible deployment of diverse image generative models. We do so by first scaling up the existing detection task setup from the one-generator to multiple-generators in training, during which we disclose two challenges presented in prior methodological designs. Specifically, we reveal that the …
abstract arxiv boom concerns cs.cv deepfake deployment detection diverse generative generative models image opportunities responsible risks robustness scaling scaling up type universal work
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US