Continual Concept Erasure in Diffusion Models by Suppressing Cross-Edit Interference

arXiv:2610.01989 · cs.CV · Submitted 2026-10-01 · Read on arXiv

cs.CV

Submitted: 2026-10-01

Updated: 2026-10-01

Comments: 24 pages. Project page: https://continual-erasure.cvmlgroup.web.illinois.edu/

Project page: https://continual-erasure.cvmlgroup.web.illinois.edu/1

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Diffusion Model — 28× in this paper · explained in 8 episodes
• Diffusion Models — 25× in this paper · explained in 6 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• Adam — 5× in this paper · explained in 2 episodes
• Benchmark — 5× in this paper · explained in 2 episodes
• Embeddings — 5× in this paper · explained in 2 episodes
• Regularization — 5× in this paper · explained in 3 episodes
• Distillation — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 3× in this paper
• Continual Learning — 3× in this paper · explained in 2 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Failure Modes — 2× in this paper · explained in 3 episodes
• Machine Unlearning — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Anchor Invariance Constraint — 1× in this paper
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Historical Orthogonality Constraint — 1× in this paper
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• Regret — 1× in this paper · explained in 3 episodes
• Synthetic Data Generation — 1× in this paper · explained in 5 episodes
• Training-Free Framework — 1× in this paper · explained in 2 episodes

Sources

• Locality-Aware Continual Unlearning for Diffusion Models
• Mass-Editing Memory in a Transformer
• Robust Concept Erasure Using Task Vectors
• Red-Teaming the Stable Diffusion Safety Filter
• Continual Unlearning for Foundational Text-to-Image Models without Generalization Erosion
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• AdvAnchor: Enhancing Diffusion Model Unlearning with Adversarial Anchors

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models