AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

QRShield: Exploiting Vulnerabilities of Latent Diffusion Models for Preventing AI Art Plagiarism

Xunyue Mo, Weibin Wu, Qingrui Tu, Hang Wang, Junxi He, Zibin Zheng

AAAI 2026 · Image generation › Autoregressive and latent generation · approach: Reconstruction-based diffusion image detection · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
raise anchor frequency from none to high (ablation)QRShield · Full U-Net fine-tuningFID: 153.11 -> 306.64Improved
use 2x2 periodic anchor tiling instead of 1x1 (ablation)QRShield · Full U-Net fine-tuningFID: 178.52 -> 306.64Improved
use finer tiling (4x4, 8x8) instead of 2x2 (ablation)QRShield · Full U-Net fine-tuningFID: 306.64 -> 226.90 (4x4), 188.82 (8x8)Hurt
share one anchor across all VAE latent channels (ablation)QRShield · Full U-Net fine-tuningFID: 274.83 -> 306.64Improved
QRShield vs Mist on full U-Net fine-tuningQRShield vs Mist · Full U-Net fine-tuningFID: 186.09 -> 306.64Improved
QRShield vs Mist on LoRA with DreamBoothQRShield vs Mist · LoRA with DreamBoothFID: 327.94 -> 382.69Improved
QRShield vs best baseline on Textual InversionQRShield vs Sim-AC · Textual InversionFID: 269.48 -> 306.49Improved
QRShield vs Mist on protection computeQRShield vs Mist · Protection efficiency (RTX 4090)time and VRAM: ~58s -> ~11s; ~16G -> ~3GImproved
transfer adversarial examples to other Stable Diffusion versionsQRShield · Cross-model transfer (full U-Net)FID: 306.64 -> 286.06 (SD1.5), 262.55 (SD1.4)Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy