AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

CopyrightShield: Enhancing Diffusion Model Security Against Copyright Infringement Attacks

Zhixiang Guo, Siyuan Liang, Aishan Liu, Dacheng Tao

ICCV 2025 · Adversarial robustness and security › Backdoor and poisoning · approach: Backdoors in large multimodal models · 2 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
add adaptive optimization training to detection (ablation)CopyrightShield (detection only) · Pokemon (poison rate 0.1)CIR: 0.517 -> 0.305Improved
add poisoned sample detection to adaptive optimization training (ablation)CopyrightShield (training only) · Pokemon (poison rate 0.1)CIR: 0.594 -> 0.305Improved
add adaptive optimization training to detection (ablation)CopyrightShield (detection only) · COYO+Midjourney (poison rate 0.1)FAE: 49.36 -> 86.42Improved
add poisoned sample detection to adaptive optimization training (ablation)CopyrightShield (training only) · COYO+Midjourney (poison rate 0.1)FAE: 35.44 -> 86.42Improved
use dynamic penalty instead of fixed lambda=0.1 (ablation)CopyrightShield · Pokemon (poison rate 0.1)CIR: 0.318 -> 0.305Improved
use dynamic penalty instead of fixed lambda=0.05 (ablation)CopyrightShield · COYO+Midjourney (poison rate 0.1)CIR: 0.237 -> 0.217Improved
use detection threshold 0.35 instead of 0.4 (ablation)CopyrightShield detection · Pokemon (rate 0.1)F1: 0.615 -> 0.671Improved
use detection threshold 0.35 instead of 0.3 (ablation)CopyrightShield detection · Pokemon (rate 0.1)F1: 0.601 -> 0.671Improved
use spatial-masked attribution instead of D-TRAKCopyrightShield detection · PokemonF1: 0.534 -> 0.671Improved
use CopyrightShield instead of TERDCopyrightShield · Pokemon (poison rate 0.1)CIR: 0.452 -> 0.305Improved
use CopyrightShield instead of T2IShieldCopyrightShield · COYO+Midjourney (poison rate 0.1)FAE: 37.85 -> 86.42Improved
defend with CopyrightShield versus attacked modelCopyrightShield · Pokemon (generation quality)FID: 54.8 -> 54.1No clear effect

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