TILDE: TILt-based Distributional Erasure for Concept Unlearning

• URL: http://arxiv.org/abs/2607.06432v1
• Date: Tue, 07 Jul 2026 15:59:59 GMT
• Title: TILDE: TILt-based Distributional Erasure for Concept Unlearning
• Abstract summary: Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment.<n>We propose TILDE, which formulates concept unlearning as a distributional alignment problem.<n>We instantiate this principle with residual $nabla$-GFlowNet training, which learns the score correction induced by the forget energy.
• Score: 42.10036183563499
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment: with rising privacy concerns, copyright disputes, trademark constraints, and safety regulations, deployed systems must be able to suppress unwanted concepts after training. Existing methods often remove the target concept effectively, but practical unlearning also requires an equally fundamental property: the unlearned model should retain quality, diversity, and semantic coverage on benign generation. The gold standard is a retain-only model trained from scratch without the unwanted data. However, common erasure objectives do not specify which post-unlearning distribution should approximate this reference, leaving retention as an implicit consequence of the update rule. We propose TILDE, TILt-based Distributional Erasure, which formulates concept unlearning as a distributional alignment problem: the desired target is the minimum-deviation conditional distribution from the pretrained model under a forgetting constraint. This energy-tilted, anchor-free target suppresses concept-expressing images while preserving benign relative mass for each prompt. We instantiate this principle with residual $\nabla$-GFlowNet training, which learns the score correction induced by the forget energy relative to the pretrained diffusion model. Across objects, artistic styles, and characters, TILDE achieves strong forgetting while improving retention and distributional fidelity over prior baselines.

Related papers

• To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion [10.950549540413528]
  Concept erasure techniques edit text-to-image diffusion models to erase undesired targets such as NSFW content or copyrighted styles.<n>Current CETs face a trade-off between erasure and utility: stronger edits erase the target more reliably but degrade utility on non-target concepts.<n>We present Preservation-aware Adaptive Ranked Subspace Expansion (PARSE), a training-free framework for robust concept erasure in latent diffusion models.
  arXiv  Detail & Related papers  (2026-07-26T06:35:31Z)
• Erasing Without Collateral Damage: Precise Concept Removal in Diffusion Models [10.269961654607108]
  Training-free concept erasure is attractive mechanism for controlling text-to-image diffusion models.<n>But precise erasure often comes at the cost of damaging semantically related non-target concepts.<n>We introduce CARE, a closed-form concept erasure operator that replaces the raw target direction with a kept-subspace-aware direction.
  arXiv  Detail & Related papers  (2026-07-06T16:21:09Z)
• CoreUnlearn: Rethinking Concept Unlearning through Disentangled Component-Level Erasure in Text-guided Diffusion Models [72.22994966489551]
  CoreUnlearn aims to disentangle and remove the erasure-critical component of the undesirable concept.<n>It achieves effective concept erasure with minimal impact on overall model performance.
  arXiv  Detail & Related papers  (2026-06-01T04:09:45Z)
• Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks [6.0599090126776565]
  Current unlearning methods share a common weakness: erased concepts return when the model is fine-tuned on downstream data.<n>We adapt Projected Gradient Unlearning from classification to the diffusion domain as a post-hoc hardening step.<n>The approach eliminates revival for style concepts and substantially delays it for object concepts, running in roughly 6 minutes versus the 2 hours required by Meta-Unlearning.
  arXiv  Detail & Related papers  (2026-04-22T19:39:56Z)
• MeGU: Machine-Guided Unlearning with Target Feature Disentanglement [73.49657372882082]
  We propose a novel framework that guides unlearning through concept-aware re-alignment.<n>MeGU enables controlled and selective forgetting, effectively mitigating both under-unlearning and over-unlearning.
  arXiv  Detail & Related papers  (2026-02-19T05:20:31Z)
• AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models [36.91937453334139]
  Concept erasure helps stop diffusion models (DMs) from generating harmful content, but current methods face retention trade off.<n>This paper introduces Adversarial Erasure with Gradient Informed Synergy (AEGIS), a retention-data-free framework that advances both robustness and retention.
  arXiv  Detail & Related papers  (2026-02-06T15:27:42Z)
• CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models [7.68494752148263]
  CURE is a training-free concept unlearning framework that operates directly in the weight space of pre-trained diffusion models.<n>The Spectral Eraser identifies and isolates features unique to the undesired concept while preserving safe attributes.<n>CURE achieves a more efficient and thorough removal for targeted artistic styles, objects, identities, or explicit content.
  arXiv  Detail & Related papers  (2025-05-19T03:53:06Z)
• Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models [56.35484513848296]
  FADE (Fine grained Attenuation for Diffusion Erasure) is an adjacency-aware unlearning algorithm for text-to-image generative models.<n>It removes target concepts with minimal impact on correlated concepts, achieving a 12% improvement in retention performance over state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-25T15:49:48Z)
• Continual Unlearning for Foundational Text-to-Image Models without Generalization Erosion [56.35484513848296]
  This research introduces continual unlearning', a novel paradigm that enables the targeted removal of multiple specific concepts from foundational generative models.<n>We propose Decremental Unlearning without Generalization Erosion (DUGE) algorithm which selectively unlearns the generation of undesired concepts.
  arXiv  Detail & Related papers  (2025-03-17T23:17:16Z)
• TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models [53.937498564603054]
  Recent advances in text-to-image diffusion models enable photorealistic image generation, but they also risk producing malicious content, such as NSFW images.<n>To mitigate risk, concept erasure methods are studied to facilitate the model to unlearn specific concepts.<n>We propose TRCE, using a two-stage concept erasure strategy to achieve an effective trade-off between reliable erasure and knowledge preservation.
  arXiv  Detail & Related papers  (2025-03-10T14:37:53Z)

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.