AI Paper Atlas

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

The Map Is Not the Territory: Embedding-Coverage Blacklists for Safe Diffusion Steering

Juyang Bai, Tong Zhou, Shaolei Ren, Xiaolin Xu

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Concept erasure in diffusion models · 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
add MAPS blacklist to SLD-MediumSLD-Medium · I2P (nudity)ASR (%): 2.53 -> 1.21Improved
add MAPS blacklist to SLD-MediumSLD-Medium · Ring-A-Bell (nudity)ASR (%): 87.71 -> 65.7Improved
add MAPS blacklist to TraSCETraSCE · Ring-A-Bell (nudity)ASR (%): 8.6 -> 5.3Improved
add MAPS blacklist to SAFREESAFREE · P4D (nudity)ASR (%): 38.4 -> 26.12Improved
add MAPS blacklist to SLD-WeakSLD-Weak · COCO-30kFID: 32.80 -> 30.12Improved
add MAPS blacklist to SLD-MaxSLD-Max · Ring-A-Bell (violence)ASR (%): 51.20 -> 3.20Improved
use high-richness long phrases instead of low-richness single words (ablation)blacklist for SLD · Ring-A-Bell (nudity)avg ASR (%): 36.15 -> 41.84Hurt
increase blacklist size from 2 to 6 keywords (ablation)SLD blacklist · Ring-A-Bell (nudity)ASR (%): 78.5 -> 76.5Improved
increase blacklist size from 6 to 8 keywords (ablation)SLD blacklist · Ring-A-Bell (nudity)ASR (%): 76.5 -> 80.0Hurt
restrict original blacklist to nudity-only concepts (ablation)SLD blacklist · Ring-A-Bell (nudity)avg ASR (%): 78.59 -> 53.24Improved
restrict original blacklist to violence-only concepts (ablation)SLD blacklist · Ring-A-Bell (violence)avg ASR (%): 75.5 -> 57.9Improved
replace manual violence blacklist with fine-grained LLM-generated keywords (ablation)SLD blacklist · Ring-A-Bell (violence)avg ASR (%): 57.9 -> 46.8Improved

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