all AI news
Regeneration Based Training-free Attribution of Fake Images Generated by Text-to-Image Generative Models
March 5, 2024, 2:48 p.m. | Meiling Li, Zhenxing Qian, Xinpeng Zhang
cs.CV updates on arXiv.org arxiv.org
Abstract: Text-to-image generative models have recently garnered significant attention due to their ability to generate images based on prompt descriptions. While these models have shown promising performance, concerns have been raised regarding the potential misuse of the generated fake images. In response to this, we have presented a simple yet effective training-free method to attribute fake images generated by text-to-image models to their source models. Given a test image to be attributed, we first inverse the …
abstract arxiv attention attribution concerns cs.ai cs.cv fake free generate generated generative generative models image images misuse performance prompt text text-to-image training type
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Senior Machine Learning Engineer
@ Samsara | Canada - Remote