IncreFA: Breaking the Static Wall of Generative Model Attribution

2026-04-19

AI Summary

Existing image provenance methods struggle to continuously adapt to rapidly evolving generative models. This work addresses this challenge by formulating it as a structured incremental learning task and, for the first time, integrating hierarchical priors of generative architectures with an incremental learning framework. Specifically, learnable orthogonal codes are employed to capture model hierarchy, while a latent memory bank stores and mixes compact latent representations to synthesize pseudo-unseen samples, effectively mitigating representation drift. Evaluated on IABench—a benchmark encompassing 28 generative models released between 2022 and 2025—the proposed method achieves a 98.93% detection rate for unseen models under a temporal open-set protocol, substantially outperforming current state-of-the-art approaches.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

As AI generative models evolve at unprecedented speed, image attribution has become a moving target. New diffusion, adversarial and autoregressive generators appear almost monthly, making existing watermark, classifier and inversion methods obsolete upon release. The core problem lies not in model recognition, but in the inability to adapt attribution itself. We introduce IncreFA, a framework that redefines attribution as a structured incremental learning problem, allowing the system to learn continuously as new generative models emerge. IncreFA departs from conventional incremental learning by exploiting the hierarchical relationships among generative architectures and coupling them with continual adaptation. It integrates two mutually reinforcing mechanisms: (1) Hierarchical Constraints, which encode architectural hierarchies through learnable orthogonal priors to disentangle family-level invariants from model-specific idiosyncrasies; and (2) a Latent Memory Bank, which replays compact latent exemplars and mixes them to generate pseudo-unseen samples, stabilising representation drift and enhancing open-set awareness. On the newly constructed Incremental Attribution Benchmark (IABench) covering 28 generative models released between 2022 and 2025, IncreFA achieves state-of-the-art attribution accuracy and 98.93% unseen detection under a temporally ordered open-set protocol. Code will be available at https://github.com/Ant0ny44/IncreFA.

Problem

• generative model attribution
• incremental learning
• open-set recognition
• model evolution
• image provenance

Innovation

• incremental learning
• hierarchical constraints
• latent memory bank
• generative model attribution
• open-set recognition