Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.06063 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913028809687040 |
|---|---|
| author | Taniguchi, Takara Shimizu, Ryohei Vo, Duc Minh Izumi, Kota Yang, Shiqi Suzuki, Teppei |
| author_facet | Taniguchi, Takara Shimizu, Ryohei Vo, Duc Minh Izumi, Kota Yang, Shiqi Suzuki, Teppei |
| contents | The advent of Text-to-Image generative models poses significant risks of copyright violation and deepfake generation. Since the rapid proliferation of new copyrighted works and private individuals constantly emerges, reference-based training-free content filters are essential for providing up-to-date protection without the constraints of a fixed knowledge cutoff. However, existing reference-based approaches often lack scalability when handling numerous references and require waiting for finishing image generation. To solve these problems, we propose EDGE-Shield, a scalable content filter during the denoising process that maintains practical latency while effectively blocking violative content. We leverage embedding-based matching for efficient reference comparison. Additionally, we introduce an \textit{$x$}-pred transformation that converts the model's noisy intermediate latent into the pseudo-estimated clean latent at the later stage, enhancing classification accuracy of violative content at earlier denoising stages. We conduct experiments of violative content filtering against two generative models including Z-Image-Turbo and Qwen-Image. EDGE-Shield significantly outperforms traditional reference-based methods in terms of latency; it achieves an approximate $79\%$ reduction in processing time for Z-Image-Turbo and approximate $50\%$ reduction for Qwen-Image, maintaining the filtering accuracy across different model architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_06063 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EDGE-Shield: Efficient Denoising-staGE Shield for Violative Content Filtering via Scalable Reference-Based Matching Taniguchi, Takara Shimizu, Ryohei Vo, Duc Minh Izumi, Kota Yang, Shiqi Suzuki, Teppei Computer Vision and Pattern Recognition Multimedia The advent of Text-to-Image generative models poses significant risks of copyright violation and deepfake generation. Since the rapid proliferation of new copyrighted works and private individuals constantly emerges, reference-based training-free content filters are essential for providing up-to-date protection without the constraints of a fixed knowledge cutoff. However, existing reference-based approaches often lack scalability when handling numerous references and require waiting for finishing image generation. To solve these problems, we propose EDGE-Shield, a scalable content filter during the denoising process that maintains practical latency while effectively blocking violative content. We leverage embedding-based matching for efficient reference comparison. Additionally, we introduce an \textit{$x$}-pred transformation that converts the model's noisy intermediate latent into the pseudo-estimated clean latent at the later stage, enhancing classification accuracy of violative content at earlier denoising stages. We conduct experiments of violative content filtering against two generative models including Z-Image-Turbo and Qwen-Image. EDGE-Shield significantly outperforms traditional reference-based methods in terms of latency; it achieves an approximate $79\%$ reduction in processing time for Z-Image-Turbo and approximate $50\%$ reduction for Qwen-Image, maintaining the filtering accuracy across different model architectures. |
| title | EDGE-Shield: Efficient Denoising-staGE Shield for Violative Content Filtering via Scalable Reference-Based Matching |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2604.06063 |