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

• URL: http://arxiv.org/abs/2607.08337v1
• Date: Thu, 09 Jul 2026 10:22:42 GMT
• Title: AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogate
• Abstract summary: Diffusion unlearning is essential for mitigating the generation of harmful or copyrighted content in text-to-image models.<n>mysysn is a two-stage framework that automatically synthesizes manifold-proximal anchors.<n>mysys effectively achieves robust and unbiased unlearning across various state-of-the-art baselines.
• Score: 3.3479862585298297
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion unlearning is essential for mitigating the generation of harmful or copyrighted content in text-to-image models. Current diffusion unlearning techniques determine the model update direction by either using alternatives of the target concept as an anchor or using empty prompts. The anchor-based method relies on manually and semantically-chosen anchors that risk biased unlearning, while the anchor-free method inherently suffers from unrobust unlearning due to unconstrained latent updates. In this work, we theoretically formalize such unstable diffusion unlearning issues under the manifold hypothesis and prove that lacking a manifold-proximal anchor inevitably induces significant normal-space drift that degrades unlearning performance. To achieve stable unlearning, we propose \mysysn, a two-stage framework that automatically synthesizes manifold-proximal anchors. However, direct geometric manifold optimization is computationally intractable. To address this challenge, \mysys introduces a novel cross-attention consistency loss which serves as a highly efficient surrogate of manifold proximity. Experimental results demonstrate that \mysys effectively achieves robust and unbiased unlearning across various state-of-the-art baselines, significantly improving targeted concept removal (by up to 31.04\% in CLIP score) and non-target utility (by up to 4.18\% in CLIP score). Moreover, \mysys can also be easily integrated into existing diffusion unlearning methods to enhance their unlearning performance (by 6.30\% for concept removal and 6.65\% for utility on average).

Related papers

• SAE-FD: Sparse Autoencoder Feature Distillation for Continual Learning of Large Language Models [21.844862497952334]
  method anchors model representations in the sparse feature space of a pre-trained Sparse Autoencoder.<n>Experiments on two continual learning benchmarks show that method consistently outperforms existing regularization-based methods.
  arXiv  Detail & Related papers  (2026-05-25T07:27:41Z)
• Sparsity-Aware Unlearning for Large Language Models [20.699929903336113]
  Large Language Models (LLMs) inevitably memorize sensitive information during training, posing significant privacy risks.<n>Machine unlearning has emerged as a promising solution to selectively remove such information without full retraining.<n>We find that unlearning effectiveness degrades substantially on sparse models.<n>We propose Sparsity-Aware Unlearning (SAU), which decouples unlearning from sparsification objectives through gradient masking.
  arXiv  Detail & Related papers  (2026-01-31T07:45:30Z)
• A Robust Certified Machine Unlearning Method Under Distribution Shift [14.904880015049208]
  We show that certified unlearning with the Newton method becomes inefficient and ineffective under non-i.i.d. unlearning sets.<n>We propose a better certified unlearning approach by performing a distribution-aware certified unlearning framework.
  arXiv  Detail & Related papers  (2026-01-11T15:53:19Z)
• Diffusion As Self-Distillation: End-to-End Latent Diffusion In One Model [53.77953728335891]
  Latent Diffusion Models rely on a complex, three-part architecture consisting of a separate encoder, decoder, and diffusion network.<n>We propose Diffusion as Self-Distillation (DSD), a new framework with key modifications to the training objective that stabilize the latent space.<n>This approach enables, for the first time, the stable end-to-end training of a single network that simultaneously learns to encode, decode, and perform diffusion.
  arXiv  Detail & Related papers  (2025-11-18T17:58:16Z)
• Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check [60.77691669644931]
  We propose Functional Alignment for Distributional Equivalence (FADE), a novel metric that measures distributional similarity between unlearned and reference models.<n>We show that FADE captures functional alignment across the entire output distribution, providing a principled assessment of genuine unlearning.<n>These findings expose fundamental gaps in current evaluation practices and demonstrate that FADE provides a more robust foundation for developing and assessing truly effective unlearning methods.
  arXiv  Detail & Related papers  (2025-10-14T20:50:30Z)
• Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning [25.53799024782883]
  Large language model (LLM) unlearning aims to surgically remove the influence of undesired data or knowledge from an existing model.<n>Recent findings reveal that unlearning manipulations such as weight quantization or fine-tuning can quickly neutralize the intended forgetting.
  arXiv  Detail & Related papers  (2025-10-01T10:50:14Z)
• Exploiting Edge Features for Transferable Adversarial Attacks in Distributed Machine Learning [54.26807397329468]
  This work explores a previously overlooked vulnerability in distributed deep learning systems.<n>An adversary who intercepts the intermediate features transmitted between them can still pose a serious threat.<n>We propose an exploitation strategy specifically designed for distributed settings.
  arXiv  Detail & Related papers  (2025-07-09T20:09:00Z)
• UniErase: Towards Balanced and Precise Unlearning in Language Models [69.04923022755547]
  Large language models (LLMs) require iterative updates to address the outdated information problem.<n>UniErase is a novel unlearning framework that demonstrates precision and balanced performances between knowledge unlearning and ability retaining.
  arXiv  Detail & Related papers  (2025-05-21T15:53:28Z)
• Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning [82.29761875805369]
  One of the ultimate goals of representation learning is to achieve compactness within a class and well-separability between classes. We propose a novel perspective to use pre-defined class anchors serving as feature centroid to unidirectionally guide feature learning. The proposed Semantic Anchor Regularization (SAR) can be used in a plug-and-play manner in the existing models.
  arXiv  Detail & Related papers  (2023-12-19T05:52:38Z)
• Imposing Consistency for Optical Flow Estimation [73.53204596544472]
  Imposing consistency through proxy tasks has been shown to enhance data-driven learning. This paper introduces novel and effective consistency strategies for optical flow estimation.
  arXiv  Detail & Related papers  (2022-04-14T22:58:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.