Learning a Semantic Similarity Orthogonal Space for Model‐Level AI ‐Generated Image Source Attribution
Expert Systems · 2026-09 · 43 (9)
DOI: 10.1111/exsy.70359 ↗Kurz gefasst
Fachartikel in der Zeitschrift Expert Systems, online erschienen am 17.07.2026. Verfasst von Yuchu Lin und 3 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Gefördert von: Basic and Applied Basic Research Foundation of Guangdong Province.
Abstract (Originalsprache)
The rapid evolution of diffusion models has established artificial intelligence generated image (AIGI) as a dominant paradigm in digital media, simultaneously escalating the risks of deepfakes and copyright infringement. While existing forensic methods focus primarily on distinguishing real from synthetic content, they fail to address the critical attribution challenge: identifying the specific model architecture responsible for a generated image. To bridge this gap, this paper proposes a novel AIGI source tracing framework capable of pinpointing source models in black‐box scenarios. Our approach is grounded in the hypothesis that images generated by the same model under identical semantic conditions exhibit consistent stylistic signatures and detail‐level artefacts. The framework operates through a ‘reconstruct‐and‐compare’ paradigm. First, we employ a CLIP‐based optimization algorithm to reconstruct the semantic prompt of the query image, enabling the generation of a reference sample from the candidate model. Second, to accurately measure the provenance similarity between the query and the reference, we introduce a Semantic Comparison Network based on Orthogonal Extension. This network utilizes a feature purification mechanism to decouple shared semantic content from model‐specific visual attributes. Furthermore, it employs a multi‐stage orthogonal training strategy to extract mutually independent feature subspaces, ensuring a comprehensive capture of diverse stylistic dimensions. Experimental results demonstrate that this framework effectively overcomes the limitations of current classifier‐based attribution, offering a robust solution for digital forensics and accountable AI governance.
Förderung
- Basic and Applied Basic Research Foundation of Guangdong Province
Zitieren
APA
Lin, Y., Jiang, X., Wang, W., & Tian, J. (2026). Learning a Semantic Similarity Orthogonal Space for Model‐Level AI ‐Generated Image Source Attribution. Expert Systems, 43(9). https://doi.org/10.1111/exsy.70359
Vancouver
Lin Y, Jiang X, Wang W, Tian J. Learning a Semantic Similarity Orthogonal Space for Model‐Level AI ‐Generated Image Source Attribution. Expert Systems. 2026;43(9). doi:10.1111/exsy.70359
BibTeX
@article{Lin2026,
author = {Lin, Yuchu and Jiang, Xinqi and Wang, Wei and Tian, Jinyu},
title = {Learning a Semantic Similarity Orthogonal Space for Model‐Level AI ‐Generated Image Source Attribution},
journal = {Expert Systems},
year = {2026},
volume = {43},
number = {9},
doi = {10.1111/exsy.70359}
}
EUVIMED