Unknown Aware AI-Generated Content Attribution

2026-01-01

arXiv.org

AI Summary

This work addresses the challenge of accurately attributing images to specific generative models—such as DALL·E 3—in open-world settings, where unknown or newly released generators are encountered. To enhance generalization to unseen models without compromising performance on known ones, the authors propose a constrained optimization framework that leverages a small amount of labeled data from the target model alongside a large corpus of unlabeled in-the-wild web images. Built upon CLIP features and a linear classifier, the method significantly improves attribution accuracy for novel and previously unobserved generative models. Experimental results demonstrate substantial gains in robustness and generalization, highlighting the critical role of unlabeled data in strengthening the reliability of AI-generated content provenance under realistic, open-world conditions.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The rapid advancement of photorealistic generative models has made it increasingly important to attribute the origin of synthetic content, moving beyond binary real or fake detection toward identifying the specific model that produced a given image. We study the problem of distinguishing outputs from a target generative model (e.g., OpenAI Dalle 3) from other sources, including real images and images generated by a wide range of alternative models. Using CLIP features and a simple linear classifier, shown to be effective in prior work, we establish a strong baseline for target generator attribution using only limited labeled data from the target model and a small number of known generators. However, this baseline struggles to generalize to harder, unseen, and newly released generators. To address this limitation, we propose a constrained optimization approach that leverages unlabeled wild data, consisting of images collected from the Internet that may include real images, outputs from unknown generators, or even samples from the target model itself. The proposed method encourages wild samples to be classified as non target while explicitly constraining performance on labeled data to remain high. Experimental results show that incorporating wild data substantially improves attribution performance on challenging unseen generators, demonstrating that unlabeled data from the wild can be effectively exploited to enhance AI generated content attribution in open world settings.

Problem

• AI-generated content attribution
• unknown generators
• open-world recognition
• model attribution
• synthetic image detection

Innovation

• unknown-aware attribution
• constrained optimization
• wild data
• CLIP features
• open-world AI attribution