AI Paper Atlas

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

TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models

Qianlong Xiang, Miao Zhang, Haoyu Zhang, Kun Wang, Junhui Hou, Liqiang Nie

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Concept erasure in diffusion models · 4 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 text-free inversion attack instead of UDAunlearned SD v1.4 (AdvUnlearn) · Nudity erasureASR: 23.24 -> 78.87Improved
use TINA instead of UDAunlearned SD v1.4 (SalUn) · Nudity erasureASR: 13.38 -> 71.13Improved
use TINA instead of UDAunlearned SD v1.4 (FMN) · Nudity erasureASR: 97.89 -> 97.89No clear effect
use TINA instead of UDAunlearned SD v1.4 (ESD) · Style erasure (Van Gogh)ASR: 32.0 -> 70.0Improved
use TINA instead of UDAunlearned SD v1.4 (AC, SPM) · Style erasure (Van Gogh)ASR: 77.0 -> 74.0 (AC); 88.0 -> 80.0 (SPM)Hurt
use TINA instead of CCEunlearned SD v1.4 (Scissorhands) · Object erasure (tench)ASR: 0.0 -> 78.0Improved
use TINA instead of CCEunlearned SD v1.4 (SalUn) · Object erasure (tench)ASR: 58.0 -> 72.0Improved
optimize inversion at each step vs standard null-text DDIM inversion (ablation)TINA · Nudity erasurereconstruction of target conceptImproved

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