mlsanityData to 14 Oct 2026

Unleashing Uncertainty: Efficient Machine Unlearning for Generative AI

arXiv 2508.20773 ↗First posted 28 Aug 2025cs.LG cs.AI cs.CVcited by 0

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

also in 1 more
Abstract (arXiv)

We introduce SAFEMax, a novel method for Machine Unlearning in diffusion models. Grounded in information-theoretic principles, SAFEMax maximizes the entropy in generated images, causing the model to generate Gaussian noise when conditioned on impermissible classes by ultimately halting its denoising process. Also, our method controls the balance between forgetting and retention by selectively focusing on the early diffusion steps, where class-specific information is prominent. Our results demonstrate the effectiveness of SAFEMax and highlight its substantial efficiency gains over state-of-the-art methods.

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 17 of its 18 references that are in the map. First posted on arXiv 28 Aug 2025.

Builds on

17 of 18 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Boosting Alignment for Post-Unlearning Text-to-Image Generative Models9 Dec
  2. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation19 Oct
  3. 2023Ablating Concepts in Text-to-Image Diffusion Models23 Mar

Other references · 14

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 618
  3. 2023Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Timecited by 439
  4. 2020Amnesiac Machine Learningcited by 319
  5. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearningcited by 279
  6. 2023Towards Unbounded Machine Unlearningcited by 268
  7. 2023Model Sparsity Can Simplify Machine Unlearningcited by 214
  8. 2023Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampeningcited by 181
  9. 2023Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Modelscited by 177
  10. 2024Are we making progress in unlearning? Findings from the first NeurIPS unlearning competitioncited by 50
  11. 2024Machine Unlearning for Image-to-Image Generative Modelscited by 47
  12. 2025Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearningcited by 19
2 more
  1. 2025LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertaintycited by 13
  2. 2024Diffusion Tuning: Transferring Diffusion Models via Chain of Forgettingcited by 12

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models
  2. 2026Unlearning for One-Step Generative Models via Unbalanced Optimal Transport
  3. 2026PECKER: A Precisely Efficient Critical Knowledge Erasure Recipe For Machine Unlearning in Diffusion Models
  4. 2026Weeding Out Bad Seeds: Initial-Noise-Robust Unlearning for Text-to-Image Diffusion Models
  5. 2026SPARE: Self-distillation for PARameter-Efficient Removal
  6. 2025ReTrack: Data Unlearning in Diffusion Models through Redirecting the Denoising Trajectory
  7. 2025Towards Irreversible Machine Unlearning for Diffusion Models
  8. 2025Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning