AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety Guidance

Yongli Xiang, Ziming Hong, Zhaoqing Wang, Xiangyu Zhao, Bo Han, Tongliang Liu

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Concept erasure in diffusion models · 13 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 CASG dynamic category selectionSLD · I2Pharmful rate (%): 12.7 -> 10.2Improved
add CASG dynamic category selectionSLD · T2VSafetyBenchharmful rate (%): 25.2 -> 9.8Improved
add CASG dynamic category selectionSLD · CoProv2harmful rate (%): 7.1 -> 3.9Improved
add CASG category selectionSAFREE · I2Pharmful rate (%): 20.0 -> 18.9Improved
add CASG category selectionSAFREE · Unsafe Diffusionharmful rate (%): 24.2 -> 17.5Improved
add CASG category selectionSAFREE · COCOFID: 43.78 -> 46.25Hurt
add CASG category selectionSLD · COCOFID: 52.11 -> 52.00No clear effect
use mismatched harmful keywords (hate) on sexual prompts (ablation)SLD · sexual promptsharmful rate (%): 67.2 -> 72.4Hurt
aggregate all harmful categories instead of matching category (sexual) (ablation)SLD · sexual promptsharmful rate (%): 3.2 -> 48.8Hurt
add hate to sexual keywords (ablation)SLD · sexual promptsharmful rate (%): 3.2 -> 5.8Hurt
replace dynamic CASG category with GPT-4o one-shot classification (ablation)SLD · T2VSafetyBenchharmful rate (%): 9.8 -> 12.3Hurt
replace dynamic CASG category with QwenGuard classification (ablation)SLD · Unsafe Diffusionharmful rate (%): 9.8 -> 23.3Hurt

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