AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate
Siyuan Wen, Jiahao Zeng, Ningning Ding
cs.LG, stat.ML
Submitted: 2026-07-09
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
- SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
- Continuous Concepts Removal in Text-to-image Diffusion Models
- Prompt-to-Prompt Image Editing with Cross Attention Control
- Diffusion Models already have a Semantic Latent Space
- Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation Misdirection
- Mass Concept Erasure in Diffusion Models with Concept Hierarchy
- Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks