arXiv AI September 15, 2026 By Qinghui Gong, Zhengchun Zhou, Hua Meng, Yihuai Liang, Yuxuan Zhang

DSS: Dynamic Semantic Steering for Robust Concept Erasure in Diffusion Models

The paper introduces Dynamic Semantic Steering (DSS), a training‑free, inference‑time defense for robust concept erasure in text‑to‑image diffusion models. DSS models local semantic neighborhoods geometrically, automatically identifies benign semantic anchors, and applies context‑aware, constrained feature correction using cross‑attention signals. Experiments show DSS achieves an average erasure rate of 91.0%, outperforming prior defenses while reducing semantic drift and preserving generation fidelity.

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 AI.

arXiv Computer Vision

Sep 14

GRACE: Adaptive Concept Erasure with Geometry-Guided Retention in Diffusion Models

GRACE is a new framework for concept erasure in text-to-image diffusion models that uses a semantically weighted sensitive subspace to guide localized interventions and lightweight subspace-constrained adapters to avoid global semantic disruption. It replaces manual counterfactual prompts with an automatically decoupled safe-anchor mechanism and controls intervention strength through an energy-driven dynamic gating system. Experiments show GRACE improves NSFW reduction by 17.86% over five state-of-the-art methods while also reducing target CLIP Score and FID, indicating stronger concept suppression with better preservation of generative quality.

By Qinghui Gong, Yihuai Liang, Yuanlun Xie, Deepak Kumar Jain, Vitomir \v{S}truc, Zhengchun Zhou

llms diffusion benchmarks

arXiv AI

Jul 23

CGCE: Classifier-Guided Concept Erasure in Generative Models

arXiv:2511. 05865v3 Announce Type: replace-cross Abstract: Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised significant safety concerns regarding the generation of unsafe content.

By Viet Nguyen, Vishal M. Patel

rag benchmarks safety

Hugging Face Trending Papers

Jul 7

AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models

Text-to-image diffusion models have achieved high visual fidelity and broad adoption, but remain vulnerable to safety violations when adversaries exploit them to synthesize illicit content. Existing alignment paradigms, from input sanitization to structural feature pruning, are largely organized around unsafe concepts explicitly exposed during filtering, editing, or localization.

diffusion efficiency multimodal safety

arXiv Computer Vision

Sep 2

Gaussian Core LoRA: Distribution-Aware Dynamic Adaptation for Broad Concept Erasure

arXiv:2609.01433v1 Announce Type: new Abstract: Concept erasure aims to suppress unsafe, privacy-sensitive, or undesirable generations in text-to-image diffusion models while preserving benign semant...

By Qinghui Gong, Xunlei Chen, Yu-Xuan Zhang, Hua Meng, Zhengchun Zhou

diffusion fine-tuning multimodal safety

arXiv AI

Aug 19

DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization

DiSCO is a zero‑shot, black‑box defense for text‑to‑image models that operates solely at the prompt level. It expands prompts with a distribution‑guided suffix using beam search and contrastive scoring against safe and unsafe image pools generated by the target model, iteratively refining until safe content is produced. The method improves safety on the I2P benchmark under various red‑teaming attacks, reducing attack success rates by 37.7% and 25.13% while preserving semantic fidelity and image coherence.

By Tong Zhang, Motasem Alfarra, Carlos Hinojosa, Christos Louizos, Bernard Ghanem

llms diffusion fine-tuning multimodal benchmarks safety

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