Explainable Artifacts for Synthetic Western Blot Source Attribution
Jo\~ao Phillipe Cardenuto, Sara Mandelli, Daniel Moreira, Paolo, Bestagini, Edward Delp, and Anderson Rocha

TL;DR
This paper investigates explainable artifacts in synthetic scientific images generated by advanced AI models to improve detection and source attribution, addressing challenges of generalization and interpretability in identifying fake images.
Contribution
It introduces methods to identify and leverage explainable artifacts in synthetic images for open-set detection and source attribution of generative models.
Findings
Identified specific artifacts in GAN and diffusion model images.
Developed explainable features for model attribution.
Enhanced detection accuracy across different generative models.
Abstract
Recent advancements in artificial intelligence have enabled generative models to produce synthetic scientific images that are indistinguishable from pristine ones, posing a challenge even for expert scientists habituated to working with such content. When exploited by organizations known as paper mills, which systematically generate fraudulent articles, these technologies can significantly contribute to the spread of misinformation about ungrounded science, potentially undermining trust in scientific research. While previous studies have explored black-box solutions, such as Convolutional Neural Networks, for identifying synthetic content, only some have addressed the challenge of generalizing across different models and providing insight into the artifacts in synthetic images that inform the detection process. This study aims to identify explainable artifacts generated by…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSpeech Recognition and Synthesis
MethodsDiffusion
