AI Paper Atlas

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

Unveiling the Attribute Misbinding Threat in Identity-Preserving Models

Junming Fu, Jishen Zeng, Yi Jiang, Peiyu Zhuang, Baoying Chen, Siyu Lu, Jianquan Yang

AAAI 2026 · Image generation › Text-to-image diffusion · approach: Fairness and bias in generative models · 1 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
use Misbinding Prompt instead of Sneakyprompttext-filter attack prompts · Text bypass, all 5 filtersbypass rate (%): 4.42 -> 40.56Improved
use Misbinding Prompt instead of I2Ptext-filter attack prompts · Text bypass, all 5 filtersbypass rate (%): 35.28 -> 40.56Improved
Misbinding Prompt vs I2P on individual filterstext-filter attack prompts · Text bypass, NSFW-TC and GPT-4obypass rate (%): 47.18 -> 44.60 (NSFW-TC); 48.90 -> 46.37 (GPT-4o)Mixed
use Misbinding Prompt instead of I2Pimage generation models · Safe Generation Rate averageS-Avg: 0.8125 -> 0.6951Improved
use Misbinding Prompt instead of I2Pimage generation models · ABSS averageABSS: 0.6597 -> 0.5894Improved
use Misbinding Prompt instead of Sneakyprompt for prompt-image alignmentimage generation models · Prompt-image alignmentA-Avg: 0.6454 -> 0.7977Improved
identity-preserving models vs foundational models under Misbinding Promptidentity-preserving models · Safe Generation RateS-Avg: 0.7275 -> 0.6756Hurt

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