Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks

• URL: http://arxiv.org/abs/2604.21041v1
• Date: Wed, 22 Apr 2026 19:39:56 GMT
• Title: Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks
• Abstract summary: 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.
• Score: 6.0599090126776565
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine unlearning for text-to-image diffusion models aims to selectively remove undesirable concepts from pre-trained models without costly retraining. Current unlearning methods share a common weakness: erased concepts return when the model is fine-tuned on downstream data, even when that data is entirely unrelated. We adapt Projected Gradient Unlearning (PGU) from classification to the diffusion domain as a post-hoc hardening step. By constructing a Core Gradient Space (CGS) from the retain concept activations and projecting gradient updates into its orthogonal complement, PGU ensures that subsequent fine-tuning cannot undo the achieved erasure. Applied on top of existing methods (ESD, UCE, Receler), 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. PGU and Meta-Unlearning turn out to be complementary: which performs better depends on how the concept is encoded, and retain concept selection should follow visual feature similarity rather than semantic grouping.

Related papers

• EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders [103.46709005379591]
  Concept erasure offers a principled remedy by removing unwanted semantics from pretrained models.<n>Existing approaches typically operate at a coarse quality, misaligned with the finegrained, distributed nature of concept representations.<n>We propose EraseSAE, a novel framework that leverages sparse autoencoders to achieve surgical concept erasure.
  arXiv  Detail & Related papers  (2026-09-03T10:23:37Z)
• TILDE: TILt-based Distributional Erasure for Concept Unlearning [42.10036183563499]
  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.
  arXiv  Detail & Related papers  (2026-07-07T15:59:59Z)
• 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)
• 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)
• ReLAPSe: Reinforcement-Learning-trained Adversarial Prompt Search for Erased concepts in unlearned diffusion models [12.021923446217722]
  Machine unlearning is a key defense mechanism for removing unauthorized concepts from text-to-image diffusion models.<n>Existing adversarial approaches for exploiting this leakage are constrained by fundamental limitations.<n>We introduce ReLAPSe, a policy-based adversarial framework that reformulates concept restoration as a reinforcement learning problem.
  arXiv  Detail & Related papers  (2026-01-30T21:56:50Z)
• Geometric-Disentangelment Unlearning [106.99160454669902]
  gradient ascent on forget samples often harms retained knowledge.<n>We propose the Geometric-disment Unlearning (GU) that decomposes any candidate forget gradient update into tangential and normal components to retain space and executes only the normal component.<n>Our method is plug-and-play and can be attached to existing gradient-based unlearning procedures to mitigate side effects.
  arXiv  Detail & Related papers  (2025-11-21T09:58:25Z)
• GrOCE:Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models [24.278300091974085]
  Concept erasure aims to remove harmful, inappropriate, or copyrighted content from text-to-image diffusion models.<n>We propose Graph-Guided Online Concept Erasure (GrOCE), a training-free framework that performs precise and adaptive concept removal.
  arXiv  Detail & Related papers  (2025-11-17T04:47:16Z)
• 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)
• Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient [20.698305103879232]
  We propose a novel concept domain correction framework named textbfDoCo (textbfDomaintextbfCorrection)<n>By aligning the output domains of sensitive and anchor concepts through adversarial training, our approach ensures comprehensive unlearning of target concepts.<n>We also introduce a concept-preserving gradient surgery technique that mitigates conflicting gradient components, thereby preserving the model's utility while unlearning specific concepts.
  arXiv  Detail & Related papers  (2024-05-24T07:47:36Z)
• Implicit Concept Removal of Diffusion Models [92.55152501707995]
  Text-to-image (T2I) diffusion models often inadvertently generate unwanted concepts such as watermarks and unsafe images. We present the Geom-Erasing, a novel concept removal method based on the geometric-driven control.
  arXiv  Detail & Related papers  (2023-10-09T17:13:10Z)

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.