ML Security PapersOmniAID: Decoupling Semantic and Artifacts for Universal AI-Generated Image Detection in the Wild
Yuncheng Guo 1, Junyan Ye 1,2, Chenjue Zhang 3, Hengrui Kang 1,4, Haohuan Fu 3, Conghui He 1, Weijia Li 1,2
Published on arXiv
2511.08423
Output Integrity Attack
OWASP ML Top 10 — ML09
Key Finding
OmniAID surpasses existing monolithic AIGI detectors on both traditional benchmarks and the new Mirage dataset by explicitly decoupling semantic and artifact representations via a hybrid MoE architecture
OmniAID
Novel technique introduced
A truly universal AI-Generated Image (AIGI) detector must simultaneously generalize across diverse generative models and varied semantic content. Current state-of-the-art methods learn a single, entangled forgery representation, conflating content-dependent flaws with content-agnostic artifacts, and are further constrained by outdated benchmarks. To overcome these limitations, we propose OmniAID, a novel framework centered on a decoupled Mixture-of-Experts (MoE) architecture. The core of our method is a hybrid expert system designed to decouple: (1) semantic flaws across distinct content domains, and (2) content-dependent flaws from content-agnostic universal artifacts. This system employs a set of Routable Specialized Semantic Experts, each for a distinct domain (e.g., human, animal), complemented by a Fixed Universal Artifact Expert. This architecture is trained using a novel two-stage strategy: we first train the experts independently with domain-specific hard-sampling to ensure specialization, and subsequently train a lightweight gating network for effective input routing. By explicitly decoupling "what is generated" (content-specific flaws) from "how it is generated" (universal artifacts), OmniAID achieves robust generalization. To address outdated benchmarks and validate real-world applicability, we introduce Mirage, a new large-scale, contemporary dataset. Extensive experiments, using both traditional benchmarks and our Mirage dataset, demonstrate our model surpasses existing monolithic detectors, establishing a new and robust standard for AIGI authentication against modern, in-the-wild threats.
Key Contributions
- OmniAID: a decoupled Mixture-of-Experts architecture pairing Routable Specialized Semantic Experts (per content domain: human, animal, etc.) with a Fixed Universal Artifact Expert to disentangle 'what is generated' from 'how it is generated'
- Two-stage training strategy: independent expert specialization via domain-specific hard-sampling, followed by lightweight gating network training for adaptive input routing
- Mirage: a new large-scale, contemporary benchmark dataset for evaluating AI-generated image detectors against modern, in-the-wild generative models
🛡️ Threat Analysis
Proposes a novel AI-generated image detection architecture (OmniAID) that distinguishes real from synthetically generated images across diverse generative models — directly addresses output integrity and content authenticity, a core ML09 concern.