Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction

TL;DR

This paper introduces SICA, a novel monolithic fake image detection model that leverages high-level semantics to reconstruct a unified yet discriminative artifact feature space, outperforming existing methods.

Contribution

Proposes the first monolithic FID paradigm, SICA, which uses semantic priors to achieve unified-yet-discriminative artifact feature space reconstruction.

Findings

SICA outperforms 15 state-of-the-art methods on OpenMMSec dataset.

SICA reconstructs the artifact feature space in a near-orthogonal manner.

The approach validates the hypothesis that high-level semantics aid feature space reconstruction.

Abstract

Fake Image Detection (FID), aiming at unified detection across four image forensic subdomains, is critical in real-world forensic scenarios. Compared with ensemble approaches, monolithic FID models are theoretically more promising, but to date, consistently yield inferior performance in practice. In this work, we identify the intrinsic distinctness of artifacts across subdomains, a critical barrier we term the ``Ji-Zhe phenomenon". Driven by this phenomenon, we diagnose the cause of this underperformance for the first time: the collapse of the artifact feature space. The core challenge for developing a practical monolithic FID model thus boils down to the ``unified-yet-discriminative" reconstruction of the artifact feature space. To address this paradoxical challenge, we hypothesize that high-level semantics can serve as a structural prior for the reconstruction, and further propose Semantic-Induced Constrained Adaptation (SICA), the first monolithic FID paradigm. Extensive experiments on our OpenMMSec dataset demonstrate that SICA outperforms 15 state-of-the-art methods and reconstructs the target unified-yet-discriminative artifact feature space in a near-orthogonal manner, thus firmly validating our hypothesis. The code and dataset are available at: https://github.com/venus-guangjian/SICA_OpenMMSec.