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

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

Home/Archive/arXiv

arXiv · 2505.15450

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

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

View original source ↗Read source document ↗Export metadata ↓

Abstract

Text-to-image diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential. However, the strong generalization capabilities of diffusion models can inadvertently lead to the generation of not-safe-for-work (NSFW) content, posing significant risks to their safe deployment. While several concept erasure methods have been proposed to mitigate the issue associated with NSFW content, a comprehensive evaluation of their effectiveness across various scenarios remains absent. To bridge this gap, we introduce a full-pipeline toolkit specifically designed for concept erasure and conduct the first systematic study of NSFW concept erasure methods. By examining the interplay between the underlying mechanisms and empirical observations, we provide in-depth insights and practical guidance for the effective application of concept erasure methods in various real-world scenarios, with the aim of advancing the understanding of content safety in diffusion models and establishing a solid foundation for future research and development in this critical area.

Explore related subjects

cs.CV

Keep this discovery

BibTeX RIS

Die Chen, Zhiwen Li, Cen Chen, Yuexiang Xie, Xiaodan Li, Jinyan Ye, Yingda Chen, Yaliang Li. 2026-08-28. Comprehensive Evaluation and Analysis for NSFW Concept Erasure in Text-to-Image Diffusion Models. https://arxiv.org/abs/2505.15450

Cite the original work for its findings. Save a collection to share your selection of sources.

Discover connections

cs.CV subject

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related papers

arXiv2026

Stochastic Optimization of Tree Tensor Networks

Tensor networks, originally developed for quantum many-body physics, are promising models for machine learning. We derive stochastic Riemannian optimizers for tree tensor networks (TTNs) on both their parameter and quotient manifolds, including adaptive and learning-rate-free schemes suitable for minibatch training. Using a hybrid CNN-TTN architecture, we evaluate the methods on Fashion-MNIST, CIFAR10, and Imagenette. The proposed optimizers achieve predictive performance comparable to unconstrained optimization while enabling numerically stable downstream compression.

math.OC↗

arXiv2026

Texture Image Classification Using DWT AlexNet Feature Fusion and Deep Neural Networks

Texture image classification plays a significant role in computer vision applications, including industrial inspection, medical image analysis, remote sensing, and object recognition. Handcrafted features can capture local texture characteristics but may have limited capability to represent complex visual patterns. In contrast, deep learning models automatically learn discriminative representations but may not fully exploit the multiscale spatial-frequency information inherent in texture images. This paper proposes a hybrid feature fusion framework, termed DWT_AlexNet_DNN, which combines Discrete Wavelet Transform (DWT) features with deep features extracted using AlexNet for texture image classification.

cs.CV↗

arXiv2026

GeBDA: Building Damage Assessment as Text-Based Sequence Prediction

Conventionally, Building Damage Assessment (BDA) is tackled either with dedicated network architectures or by fine-tuning geospatial image foundation models. In this work, we ask whether a general-purpose Vision-Language Model (VLM) can localize buildings and grade their damage through autoregressive sequence generation alone. We cast BDA as predicting a variable-length set of bounding boxes, each specified by its coordinates and a damage label. Our preliminary implementation, based on the open Gemma model, achieves promising damage mapping results from only bi-temporal satellite images and a suitable text prompt.

cs.CV↗