Image de couverture de livre

Robust Concept Erasure in Diffusion Models: A Theoretical Perspective on Security and Robustness

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Fu, Zixuan, Ren, Yan, Carter, Finn, Wen, Chenyue, Ku, Le, Yu, Daheng, Davis, Emily, Zhang, Bo
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

FADE: Adversarial Concept Erasure in Flow Models
par: Fu, Zixuan, et autres
Publié: (2025)

ACE: Attentional Concept Erasure in Diffusion Models
par: Carter, Finn
Publié: (2025)

TRACE: Trajectory-Constrained Concept Erasure in Diffusion Models
par: Carter, Finn
Publié: (2025)

Diffusion-Based Image Editing for Breaking Robust Watermarks
par: Ni, Yunyi, et autres
Publié: (2025)

Rethinking Robust Adversarial Concept Erasure in Diffusion Models
par: Yin, Qinghong, et autres
Publié: (2025)

R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model
par: Kim, Changhoon, et autres
Publié: (2024)

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
par: Zhang, Yimeng, et autres
Publié: (2024)

Robust Concept Erasure Using Task Vectors
par: Pham, Minh, et autres
Publié: (2024)

M-ErasureBench: A Comprehensive Multimodal Evaluation Benchmark for Concept Erasure in Diffusion Models
par: Weng, Ju-Hsuan, et autres
Publié: (2025)

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models
par: Nguyen, Kien, et autres
Publié: (2025)

Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models
par: Gong, Chao, et autres
Publié: (2024)

Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models
par: Xiong, Lexiang, et autres
Publié: (2025)

Mass Concept Erasure in Diffusion Models with Concept Hierarchy
par: Tu, Jiahang, et autres
Publié: (2026)

SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models
par: Li, Ouxiang, et autres
Publié: (2025)

Dynamic Eraser for Guided Concept Erasure in Diffusion Models
par: Gong, Qinghui
Publié: (2026)

Separable Multi-Concept Erasure from Diffusion Models
par: Zhao, Mengnan, et autres
Publié: (2024)

MACE: Mass Concept Erasure in Diffusion Models
par: Lu, Shilin, et autres
Publié: (2024)

Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them
par: Bui, Anh, et autres
Publié: (2025)

Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models
par: Xie, Yiwei, et autres
Publié: (2026)

GrOCE:Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models
par: Han, Ning, et autres
Publié: (2025)

Prototype-Guided Concept Erasure in Diffusion Models
par: Cai, Yuze, et autres
Publié: (2026)

Pruning for Robust Concept Erasing in Diffusion Models
par: Yang, Tianyun, et autres
Publié: (2024)

Robust Provably Secure Image Steganography via Latent Iterative Optimization
par: Li, Yanan, et autres
Publié: (2026)

Comprehensive Evaluation and Analysis for NSFW Concept Erasure in Text-to-Image Diffusion Models
par: Chen, Die, et autres
Publié: (2025)

A Comprehensive Survey on Concept Erasure in Text-to-Image Diffusion Models
par: Kim, Changhoon, et autres
Publié: (2025)

Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models
par: Shi, Zhuan, et autres
Publié: (2026)

Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models
par: Zhang, Zhiqi, et autres
Publié: (2026)

VideoEraser: Concept Erasure in Text-to-Video Diffusion Models
par: Xu, Naen, et autres
Publié: (2025)

A Single Neuron Works: Precise Concept Erasure in Text-to-Image Diffusion Models
par: He, Qinqin, et autres
Publié: (2025)

Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models
par: Seo, Hoigi, et autres
Publié: (2026)

Minimalist Concept Erasure in Generative Models
par: Zhang, Yang, et autres
Publié: (2025)

Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers
par: Jiang, Nanxiang, et autres
Publié: (2026)

BARRIER: Bounded Activation Regions for Robust Information Erasure
par: Miksa, Jan, et autres
Publié: (2026)

TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models
par: Chen, Ruidong, et autres
Publié: (2025)

TrackerSplat: Exploiting Point Tracking for Fast and Robust Dynamic 3D Gaussians Reconstruction
par: Yin, Daheng, et autres
Publié: (2026)

Towards Robust and Reliable Concept Representations: Reliability-Enhanced Concept Embedding Model
par: Cai, Yuxuan, et autres
Publié: (2025)

ACE: Anti-Editing Concept Erasure in Text-to-Image Models
par: Wang, Zihao, et autres
Publié: (2025)

Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs
par: Fang, Xianya, et autres
Publié: (2026)

On the Information-Theoretic Fragility of Robust Watermarking under Diffusion Editing
par: Ni, Yunyi, et autres
Publié: (2025)

CRCE: Coreference-Retention Concept Erasure in Text-to-Image Diffusion Models
par: Xue, Yuyang, et autres
Publié: (2025)