arXiv Computer Vision August 31, 2026 By Die Chen, Zhiwen Li, Cen Chen, Yuexiang Xie, Xiaodan Li, Jinyan Ye, Yingda Chen, Yaliang Li

Comprehensive Evaluation and Analysis for NSFW Concept Erasure in Text-to-Image Diffusion Models

Read the original on arXiv Computer Vision →

The paper presents a comprehensive toolkit for evaluating and analyzing NSFW concept erasure in text-to-image diffusion models. It conducts the first systematic study of existing erasure methods, exploring how their mechanisms interact with empirical results. The authors offer detailed insights and practical guidance to improve content safety in diffusion models across real-world scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computer Vision

Sep 1

Comprehensive Assessment and Analysis for NSFW Content Erasure in Text-to-Image Diffusion Models

arXiv:2502.12527v2 Announce Type: replace Abstract: Text-to-image diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential. However, the...

By Die Chen, Zhiwen Li, Cen Chen, Yuexiang Xie, Xiaodan Li, Jinyan Ye, Yingda Chen, Yaliang Li

diffusion safety

arXiv AI

Jun 2

Erased but Not Forgotten: How Backdoors Compromise Concept Erasure

arXiv:2504. 21072v2 Announce Type: replace-cross Abstract: The expansion of text-to-image diffusion models has raised concerns about harmful outputs, from fabricated depictions of public figures to sexually explicit imagery.

By Tobias Braun, Jonas Henry Grebe, Marcus Rohrbach, Anna Rohrbach

diffusion fine-tuning benchmarks

arXiv Machine Learning

Jul 28

To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion

arXiv:2607. 23492v1 Announce Type: cross Abstract: Concept erasure techniques (CETs) edit text-to-image diffusion models to erase undesired targets such as NSFW content or copyrighted styles, while preserving model utility on benign concepts.

By Shaswati Saha, Rajasekhar Anguluri, Manas Gaur

llms diffusion multimodal

arXiv Computer Vision

2d ago

RASteer: Retain-Aware Activation Steering for Concept Erasure in Diffusion Models

arXiv:2610.01969v1 Announce Type: new Abstract: Concept erasure aims to remove a target concept, such as a copyrighted style, a recognizable character, or unsafe content, from a pretrained text-to-im...

By Yongliang Wu, Haori Lu, Yulun Wu, Jinqi Luo, Xingyu Zhu, Yaoyao Liu

diffusion benchmarks

arXiv Machine Learning

Sep 14

Certifying Concept Unlearning in Text-to-Image Diffusion Models

The paper introduces a certification framework for assessing concept unlearning in text-to-image diffusion models, offering high‑confidence guarantees with bounded error on residual concept leakage. Unlike prior methods that rely solely on attack success rates from automated prompt searches, this approach combines statistical certification with worst‑case analysis along concept‑relevant embedding directions to derive explicit upper bounds on leakage probability. Evaluations across NSFW content, artistic styles, and celebrity identities reveal that certified leakage bounds exceed standard attack success rates by 16.2%, highlighting significant residual risks overlooked by existing protocols.

By Mansi, Luca Marzari, Francesco Leofante

rag diffusion benchmarks safety

Hugging Face Trending Papers

Jul 6

Erasing Without Collateral Damage: Precise Concept Removal in Diffusion Models

Training-free concept erasure is an attractive mechanism for controlling text-to-image diffusion models, but precise erasure often comes at the cost of damaging semantically related non-target concepts. Existing value-space methods remove the component of each cross-attention value along the target concept direction, implicitly treating target identity and shared visual structure as the same signal.

diffusion fine-tuning