UniMark: Artificial Intelligence Generated Content Identification Toolkit

The rapid proliferation of Artificial Intelligence Generated Content has precipitated a crisis of trust and urgent regulatory demands. However, existing identification tools suffer from fragmentation and a lack of support for visible compliance marking. To address these gaps, we introduce the \textbf{UniMark}, an open-source, unified framework for multimodal content governance. Our system features a modular unified engine that abstracts complexities across text, image, audio, and video modalities. Crucially, we propose a novel dual-operation strategy, natively supporting both \emph{Hidden Watermarking} for copyright protection and \emph{Visible Marking} for regulatory compliance. Furthermore, we establish a standardized evaluation framework with three specialized benchmarks (Image/Video/Audio-Bench) to ensure rigorous performance assessment. This toolkit bridges the gap between advanced algorithms and engineering implementation, fostering a more transparent and secure digital ecosystem.

Key Contributions

Unified, modular open-source engine abstracting AIGC identification across text, image, audio, and video modalities
Dual-operation strategy natively supporting both hidden watermarking (copyright/provenance) and visible marking (regulatory compliance)
Standardized evaluation framework with three specialized benchmarks (Image-Bench, Video-Bench, Audio-Bench) for rigorous performance assessment

🛡️ Threat Analysis

Output Integrity Attack

Primary contribution is watermarking and identifying AI-generated content (text, image, audio, video) — hidden watermarking for copyright/provenance and visible marking for regulatory compliance are both output integrity concerns. Benchmarks assess AIGC detection performance across modalities.