Saved in:
Bibliographic Details
Main Authors: Taniguchi, Takara, Shimizu, Ryohei, Vo, Duc Minh, Izumi, Kota, Yang, Shiqi, Suzuki, Teppei
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