Beyond Fixed Anchors: Precisely Erasing Concepts with Sibling Exclusive Counterparts

• URL: http://arxiv.org/abs/2510.16342v1
• Date: Sat, 18 Oct 2025 04:03:27 GMT
• Title: Beyond Fixed Anchors: Precisely Erasing Concepts with Sibling Exclusive Counterparts
• Authors: Tong Zhang, Ru Zhang, Jianyi Liu, Zhen Yang, Gongshen Liu,
• Abstract summary: We propose a dynamic anchor selection framework designed to overcome the limitations of fixed anchors.<n>Our framework introduces a novel two-stage evaluation mechanism that automatically discovers optimal anchors for precise erasure.<n>Extensive evaluations demonstrate that SELECT, as a universal anchor solution, not only efficiently adapts to multiple erasure frameworks but also consistently outperforms existing baselines.
• Score: 41.76408183825337
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing concept erasure methods for text-to-image diffusion models commonly rely on fixed anchor strategies, which often lead to critical issues such as concept re-emergence and erosion. To address this, we conduct causal tracing to reveal the inherent sensitivity of erasure to anchor selection and define Sibling Exclusive Concepts as a superior class of anchors. Based on this insight, we propose \textbf{SELECT} (Sibling-Exclusive Evaluation for Contextual Targeting), a dynamic anchor selection framework designed to overcome the limitations of fixed anchors. Our framework introduces a novel two-stage evaluation mechanism that automatically discovers optimal anchors for precise erasure while identifying critical boundary anchors to preserve related concepts. Extensive evaluations demonstrate that SELECT, as a universal anchor solution, not only efficiently adapts to multiple erasure frameworks but also consistently outperforms existing baselines across key performance metrics, averaging only 4 seconds for anchor mining of a single concept.

Related papers

• Consistency-Preserving Concept Erasure via Unsafe-Safe Pairing and Directional Fisher-weighted Adaptation [17.59828667571619]
  Existing concept erasure approaches focus on removing unsafe concepts without providing guidance toward corresponding safe alternatives.<n>We propose a novel framework, PAIRed Erasing, which reframes concept erasure from simple removal to consistency-preserving semantic realignment.<n>Our approach significantly outperforms state-of-the-art baselines, achieving effective concept erasure while preserving structural integrity, semantic coherence, and generation quality.
  arXiv  Detail & Related papers  (2026-02-05T06:05:24Z)
• DyME: Dynamic Multi-Concept Erasure in Diffusion Models with Bi-Level Orthogonal LoRA Adaptation [11.480659591569308]
  Text-to-image diffusion models inadvertently reproduce copyrighted styles and protected visual concepts, raising legal and ethical concerns.<n> Concept erasure has emerged as a safeguard, aiming to selectively suppress such concepts through fine-tuning.<n>We propose DyME, an on-demand erasure framework that trains lightweight, concept-specific LoRA adapters and dynamically composes only those needed at inference.
  arXiv  Detail & Related papers  (2025-09-25T15:16:17Z)
• ERIS: An Energy-Guided Feature Disentanglement Framework for Out-of-Distribution Time Series Classification [51.07970070817353]
  An ideal time series classification (TSC) should be able to capture invariant representations.<n>Current methods are largely unguided, lacking the semantic direction required to isolate truly universal features.<n>We propose an end-to-end Energy-Regularized Information for Shift-Robustness framework to enable guided and reliable feature disentanglement.
  arXiv  Detail & Related papers  (2025-08-19T12:13:41Z)
• Zero-Residual Concept Erasure via Progressive Alignment in Text-to-Image Model [15.636542463543066]
  Concept Erasure aims to prevent pretrained text-to-image models from generating content associated with semantic-harmful concepts.<n>Existing methods often result in incomplete erasure due to "non-zero alignment residual"<n>We propose a novel closed-form method ErasePro: it is designed for more complete concept erasure and better preserving overall generative quality.
  arXiv  Detail & Related papers  (2025-08-06T14:19:32Z)
• Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts [12.04985139116705]
  We introduce a finetuning framework, dubbed ANT, which guides deNoising Trajectories to avoid unwanted concepts.<n>ANT is built on a key insight: reversing the condition direction of classifier-free guidance during mid-to-late denoising stages.<n>For single-concept erasure, we propose an augmentation-enhanced weight saliency map, enabling more thorough and efficient erasure.<n>For multi-concept erasure, our objective function offers a versatile plug-and-play solution that significantly boosts performance.
  arXiv  Detail & Related papers  (2025-04-17T09:29:30Z)
• SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models [56.83154571623655]
  We introduce SPEED, an efficient concept erasure approach that directly edits model parameters.<n>Speedy searches for a null space, a model editing space where parameter updates do not affect non-target concepts.<n>We successfully erase 100 concepts within only 5 seconds.
  arXiv  Detail & Related papers  (2025-03-10T14:40:01Z)
• AdvAnchor: Enhancing Diffusion Model Unlearning with Adversarial Anchors [61.007590285263376]
  Security concerns have driven researchers to unlearn inappropriate concepts through fine-tuning.<n>Recent fine-tuning methods exhibit a considerable performance trade-off between eliminating undesirable concepts and preserving other concepts.<n>We propose AdvAnchor, a novel approach that generates adversarial anchors to alleviate the trade-off issue.
  arXiv  Detail & Related papers  (2024-12-28T04:44:07Z)
• Boundary Discretization and Reliable Classification Network for Temporal Action Detection [39.17204328036531]
  Temporal action detection aims to recognize the action category and determine each action instance's starting and ending time in untrimmed videos. Mixed methods have achieved remarkable performance by seamlessly merging anchor-based and anchor-free approaches. We propose a novel Boundary Discretization and Reliable Classification Network (BDRC-Net) that addresses the issues above by introducing boundary discretization and reliable classification modules.
  arXiv  Detail & Related papers  (2023-10-10T08:14:24Z)
• A general framework for defining and optimizing robustness [74.67016173858497]
  We propose a rigorous and flexible framework for defining different types of robustness properties for classifiers. Our concept is based on postulates that robustness of a classifier should be considered as a property that is independent of accuracy. We develop a very general robustness framework that is applicable to any type of classification model.
  arXiv  Detail & Related papers  (2020-06-19T13:24:20Z)
• Scope Head for Accurate Localization in Object Detection [135.9979405835606]
  We propose a novel detector coined as ScopeNet, which models anchors of each location as a mutually dependent relationship. With our concise and effective design, the proposed ScopeNet achieves state-of-the-art results on COCO.
  arXiv  Detail & Related papers  (2020-05-11T04:00:09Z)

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.