arXiv Computer Vision

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.

arXiv AI

Sep 15

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.

By Qinghui Gong, Zhengchun Zhou, Hua Meng, Yihuai Liang, Yuxuan Zhang

diffusion robotics 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 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 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 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

arXiv AI

Jun 16

SACE: Concept Erasure at the Semantic Singularity in Visual Autoregressive Models

arXiv:2606. 15819v1 Announce Type: cross Abstract: The rapid progress of visual autoregressive (VAR) models has unlocked a transformative frontier for high-fidelity text-to-image synthesis, while heightening concerns over the safety alignment of generated content.

By Siya Yang, Nanxiang Jiang, Zhaoxin Fan, Yunfeng Diao

diffusion safety

arXiv Computation and Language

Sep 1

Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings

arXiv:2606.03695v2 Announce Type: replace Abstract: As language models are increasingly deployed in real-world applications, the ability to erase specific knowledge from them becomes critical for saf...

By Clara Haya Suslik, Or Shafran, Mor Geva

llms rag safety

arXiv Machine Learning

Jul 7

MANCE: Manifold Aware Concept Erasure

arXiv:2607. 03973v1 Announce Type: new Abstract: Concept erasure aims to remove a target concept from a representation while preserving the other information encoded in it.

By Matan Avitan, Yoav Goldberg, Yanai Elazar

llms nlp benchmarks

Hugging Face Trending Papers

Aug 24

Continual Visual Learning under Evolving Semantic Concept Shift

Visual foundation models are commonly adapted under the assumption that the appearance of incoming data may change while the semantic meaning of the prediction task remains fixed. In long-lived visual...

fine-tuning

Hugging Face Trending Papers

Jul 4

MANCE: Manifold Aware Concept Erasure

Concept erasure aims to remove a target concept from a representation while preserving the other information encoded in it. This is difficult because representations encode many concepts that are often correlated with the erasure target, so removing the target risks damaging them.

llms nlp benchmarks

arXiv Machine Learning

Jul 10

AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate

arXiv:2607. 08337v1 Announce Type: new Abstract: Diffusion unlearning is essential for mitigating the generation of harmful or copyrighted content in text-to-image models.

By Siyuan Wen, Jiahao Zeng, Ningning Ding

diffusion benchmarks

arXiv Computation and Language

Aug 21

ConceptGuard: Benchmarking Context-Sensitive Unlearning in Large Language Models

arXiv:2608. 20338v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly require selective removal of harmful or sensitive knowledge, called unlearning, yet existing methods and benchmarks fail to evaluate this capability completely.

By Sahil Kale, Ian Harris

llms benchmarks safety

Related stories