Synthetic Image Verification in the Era of Generative AI: What Works and What Isn't There Yet
In this work we present an overview of approaches for the detection and attribution of synthetic images and highlight their strengths and weaknesses. We also point out and discuss hot topics in this field and outline promising directions for future research.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Generating Synthetic Satellite Imagery With Deep-Learning Text-to-Image Models -- Technical Challenges and Implications for Monitoring and Verification
Novel deep-learning (DL) architectures have reached a level where they can generate digital media, including photorealistic images, that are difficult to distinguish from real data. These technologies have already been u…
Image GenerationImage-to-Image Translation Based on Deep Generative Modeling for Radiotherapy Synthetic Dataset Creation
Objective: Radiotherapy uses precise doses of radiation to treat cancer, requiring accurate verification, e.g. using the Electronic Portal Imaging Device (EPID), to guide treatment. To develop an effective artificial int…
Image-to-Image TranslationTranslationUnsupervised Image-To-Image TranslationWhat can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networks
In recent decades, Generative Adversarial Network (GAN) and its variants have achieved unprecedented success in image synthesis. However, well-trained GANs are under the threat of illegal steal or leakage. The prior …
Generative Adversarial NetworkImage GenerationTraining Data Provenance Verification: Did Your Model Use Synthetic Data from My Generative Model for Training?
High-quality open-source text-to-image models have lowered the threshold for obtaining photorealistic images significantly, but also face potential risks of misuse. Specifically, suspects may use synthetic data generated…
modelA Siamese-based Verification System for Open-set Architecture Attribution of Synthetic Images
Despite the wide variety of methods developed for synthetic image attribution, most of them can only attribute images generated by models or architectures included in the training set and do not work with unknown archite…
AttributeImage AttributionImage GenerationSynthetic Image Attribution