Image de couverture de livre

Roots Beneath the Cut: Uncovering the Risk of Concept Revival in Pruning-Based Unlearning for Diffusion Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Ci, Ding, Zhaojun, Yang, Chence, Liu, Jun, Zhai, Xiaoming, Huang, Shaoyi, Li, Beiwen, Ma, Xiaolong, Lu, Jin, Yuan, Geng
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Rethinking the Potential of Layer Freezing for Efficient DNN Training
par: Yang, Chence, et autres
Publié: (2025)

Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
par: Deng, Kaiyuan, et autres
Publié: (2026)

ACE: Exploring Activation Cosine Similarity and Variance for Accurate and Calibration-Efficient LLM Pruning
par: Mi, Zhendong, et autres
Publié: (2025)

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks
par: Aladawi, Aljalila, et autres
Publié: (2026)

Trading Power: The Gender Politics Beneath America's Labor Revival
par: Amanda Furiasse
Publié: (2025)

Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models
par: Deng, Kaiyuan, et autres
Publié: (2026)

The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models
par: Xiao, Yang, et autres
Publié: (2025)

End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost
par: Tan, Qitao, et autres
Publié: (2025)

Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models
par: Suriyakumar, Vinith M., et autres
Publié: (2024)

Generative Large Language Models for Knowledge Representation: A Systematic Review of Concept Map Generation
par: Zhai, Xiaoming
Publié: (2025)

A Simple Linear Patch Revives Layer-Pruned Large Language Models
par: Chen, Xinrui, et autres
Publié: (2025)

Uncovering the Potential Risks in Unlearning: Danger of English-only Unlearning in Multilingual LLMs
par: Hwang, Kyomin, et autres
Publié: (2025)

Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
par: Kim, Hyeonjin, et autres
Publié: (2026)

What Lurks Within? Concept Auditing for Shared Diffusion Models at Scale
par: Yuan, Xiaoyong, et autres
Publié: (2025)

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts
par: Gao, Hongcheng, et autres
Publié: (2024)

ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning
par: Chavhan, Ruchika, et autres
Publié: (2024)

Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models
par: Moon, Saemi, et autres
Publié: (2026)

Advancing time series completion via RFAMoE and MDFF
par: Zhang, Ci, et autres
Publié: (2025)

AutoSCORE: Enhancing Automated Scoring with Multi-Agent Large Language Models via Structured Component Recognition
par: Wang, Yun, et autres
Publié: (2025)

Perturbation-efficient Zeroth-order Optimization for Hardware-friendly On-device Training
par: Tan, Qitao, et autres
Publié: (2025)

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

Learning to Unlearn for Robust Machine Unlearning
par: Huang, Mark He, et autres
Publié: (2024)

Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient
par: Wu, Yongliang, et autres
Publié: (2024)

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

ART: Distribution-Free and Model-Agnostic Changepoint Detection with Finite-Sample Guarantees
par: Cui, Xiaolong, et autres
Publié: (2025)

Concept Unlearning by Modeling Key Steps of Diffusion Process
par: Zhang, Chaoshuo, et autres
Publié: (2025)

Unlearning Concepts from Text-to-Video Diffusion Models
par: Liu, Shiqi, et autres
Publié: (2024)

SPAP: Structured Pruning via Alternating Optimization and Penalty Methods
par: Hu, Hanyu, et autres
Publié: (2025)

Topology-Aware Revival for Efficient Sparse Training
par: Jin, Meiling, et autres
Publié: (2026)

Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning
par: Tan, Qitao, et autres
Publié: (2025)

Foundation Models for Low-Resource Language Education (Vision Paper)
par: Ding, Zhaojun, et autres
Publié: (2024)

ToMA: Token Merge with Attention for Diffusion Models
par: Lu, Wenbo, et autres
Publié: (2025)

SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders
par: Li, Qing, et autres
Publié: (2025)

Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models
par: Shirkavand, Reza, et autres
Publié: (2024)

CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models
par: Biswas, Shristi Das, et autres
Publié: (2025)

SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders
par: Cywiński, Bartosz, et autres
Publié: (2025)

Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models
par: Liu, Zheyuan, et autres
Publié: (2025)

Beneath the Tasman Sea
par: Doubilet, David
Publié: (1997)

CoreUnlearn: Rethinking Concept Unlearning through Disentangled Component-Level Erasure in Text-guided Diffusion Models
par: Zhao, Mengnan, et autres
Publié: (2026)

Orthogonal Soft Pruning for Efficient Class Unlearning
par: Gong, Qinghui, et autres
Publié: (2025)