mlsanityData to 14 Oct 2026

PECKER: A Precisely Efficient Critical Knowledge Erasure Recipe For Machine Unlearning in Diffusion Models

arXiv 2604.05634 ↗First posted 7 Apr 2026cs.AIcited by 0

On the map: Diffusion models → Robustness, privacy and adversarial aspects

also in 1 more
Abstract (arXiv)

Machine unlearning (MU) has become a critical technique for GenAI models' safe and compliant operation. While existing MU methods are effective, most impose prohibitive training time and computational overhead. Our analysis suggests the root cause lies in poorly directed gradient updates, which reduce training efficiency and destabilize convergence. To mitigate these issues, we propose PECKER, an efficient MU approach that matches or outperforms prevailing methods. Within a distillation framework, PECKER introduces a saliency mask to prioritize updates to parameters that contribute most to forgetting the targeted data, thereby reducing unnecessary gradient computation and shortening overall training time without sacrificing unlearning efficacy. Our method generates samples that unlearn related class or concept more quickly, while closely aligning with the true image distribution on CIFAR-10 and STL-10 datasets, achieving shorter training times for both class forgetting and concept forgetting.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 34 of its 42 references that are in the map. First posted on arXiv 7 Apr 2026.

Builds on

34 of 42 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models17 Sep
  2. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation19 Oct
  3. 2023Erasing Concepts from Diffusion Models13 Mar
  4. 2022Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models9 Nov

Other references · 30

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  5. 2022Classifier-Free Diffusion Guidancecited by 5,847
  6. 2016Improved Techniques for Training GANscited by 2,970
  7. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  8. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  9. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  10. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  11. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  12. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
18 more
  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  2. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  3. 2023One-step Diffusion with Distribution Matching Distillationcited by 1,019
  4. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  5. 2021Knowledge Neurons in Pretrained Transformerscited by 601
  6. 2021Editing Factual Knowledge in Language Modelscited by 553
  7. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generationcited by 214
  8. 2023Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Modelscited by 177
  9. 2023Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attackscited by 158
  10. 2020Rewriting a Deep Generative Modelcited by 107
  11. 2025Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecastingcited by 55
  12. 2025Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodalitycited by 50
  13. 2025SepPrune: Structured Pruning for Efficient Deep Speech Separationcited by 31
  14. 2022Data Redaction from Pre-trained GANscited by 18
  15. 2024Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Modelscited by 17
  16. 2023Less is More: Data Pruning for Faster Adversarial Trainingcited by 13
  17. 2024Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generationcited by 13
  18. 2025HDCompression: Hybrid-Diffusion Image Compression for Ultra-Low Bitratescited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026SPARE: Self-distillation for PARameter-Efficient Removal
  2. 2026Unlearning the Unpromptable: Prompt-free Instance Unlearning in Diffusion Models
  3. 2026Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models
  4. 2026Compensation-free Machine Unlearning in Text-to-Image Diffusion Models by Eliminating the Mutual Information
  5. 2025Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning
  6. 2025Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning
  7. 2025Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective
  8. 2026Roots Beneath the Cut: Uncovering the Risk of Concept Revival in Pruning-Based Unlearning for Diffusion Models