# ForgetMe: Evaluating Selective Forgetting in Generative Models

arXiv: https://arxiv.org/abs/2504.12574 · HTML: https://mlsanity.com/paper/2504.12574/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 48 of its 83 references that are in the map.
- First posted on arXiv 17 Apr 2025.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)
- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Builds on (most cited first, 30 of 48)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Erasing Concepts from Diffusion Models](https://mlsanity.com/paper/2303.07345/) (2023)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Analyzing and Mitigating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2310.00754/) (2023)
- [Rethinking FID: Towards a Better Evaluation Metric for Image Generation](https://mlsanity.com/paper/2401.09603/) (2023)
- [MACE: Mass Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2403.06135/) (2024)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models](https://mlsanity.com/paper/2305.10120/) (2023)
- [Effectively Unbiased FID and Inception Score and where to find them](https://mlsanity.com/paper/1911.07023/) (2019)
- [Towards Safer Large Language Models through Machine Unlearning](https://mlsanity.com/paper/2402.10058/) (2024)
- [Transparent Image Layer Diffusion using Latent Transparency](https://mlsanity.com/paper/2402.17113/) (2024)
- [Lumina-Image 2.0: A Unified and Efficient Image Generative Framework](https://mlsanity.com/paper/2503.21758/) (2025)
- [Machine Unlearning: Solutions and Challenges](https://mlsanity.com/paper/2308.07061/) (2023)
- [Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey](https://mlsanity.com/paper/2412.20367/) (2024)
- [Calibrated Self-Rewarding Vision Language Models](https://mlsanity.com/paper/2405.14622/) (2024)
- [Fast Model Debias with Machine Unlearning](https://mlsanity.com/paper/2310.12560/) (2023)
- [Inst-Inpaint: Instructing to Remove Objects with Diffusion Models](https://mlsanity.com/paper/2304.03246/) (2023)
- [A Survey on Federated Unlearning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/2310.20448/) (2023)
- [VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding](https://mlsanity.com/paper/2312.08733/) (2023)
- [Self-evolving Agents with reflective and memory-augmented abilities](https://mlsanity.com/paper/2409.00872/) (2024)
- [Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model](https://mlsanity.com/paper/2405.15330/) (2024)
- [SCORE: Story Coherence and Retrieval Enhancement for AI Narratives](https://mlsanity.com/paper/2503.23512/) (2025)
- [LayerDiffusion: Layered Controlled Image Editing with Diffusion Models](https://mlsanity.com/paper/2305.18676/) (2023)

## Built on by (most cited first, 11 of 11)

- [FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving](https://mlsanity.com/paper/2505.17685/) (2025)
- [Mitigating Hallucination on Hallucination in RAG via Ensemble Voting](https://mlsanity.com/paper/2603.27253/) (2026)
- [ICU-Bench:Benchmarking Continual Unlearning in Multimodal Large Language Models](https://mlsanity.com/paper/2605.05938/) (2026)
- [Do Vision Models Truly Forget? New Findings from Representation-Level Certification of Visual Unlearning in Vertical Federated Learning](https://mlsanity.com/paper/2605.20282/) (2026)
- [An Open-Source Benchmark and Baseline for Multi-temporal Referring Segmentation](https://mlsanity.com/paper/2606.00987/) (2026)
- [Multi-Modal Machine Learning Framework for Predicting Early Recurrence of Brain Tumors Using MRI and Clinical Biomarkers](https://mlsanity.com/paper/2509.01161/) (2025)
- [A Multimodal Deep Learning Framework for Early Diagnosis of Liver Cancer via Optimized BiLSTM-AM-VMD Architecture](https://mlsanity.com/paper/2509.01164/) (2025)
- [Adaptive Multi-Stage Patent Claim Generation with Unified Quality Assessment](https://mlsanity.com/paper/2601.09120/) (2026)
- [InstantForget: Update-Free Backdoor Unlearning with Inference-Time Feature Reset](https://mlsanity.com/paper/2606.15730/) (2026)
- [FedCausal-Dyn: A Causal-Dynamic Paradigm for Federated Learning under Dynamic Feature Drift](https://mlsanity.com/paper/2607.09695/) (2026)
- [A Model Merging Approach for Continual MLLM Unlearning](https://mlsanity.com/paper/2608.04548/) (2026)

## Abstract (arXiv)

The widespread adoption of diffusion models in image generation has increased the demand for privacy-compliant unlearning. However, due to the high-dimensional nature and complex feature representations of diffusion models, achieving selective unlearning remains challenging, as existing methods struggle to remove sensitive information while preserving the consistency of non-sensitive regions. To address this, we propose an Automatic Dataset Creation Framework based on prompt-based layered editing and training-free local feature removal, constructing the ForgetMe dataset and introducing the Entangled evaluation metric. The Entangled metric quantifies unlearning effectiveness by assessing the similarity and consistency between the target and background regions and supports both paired (Entangled-D) and unpaired (Entangled-S) image data, enabling unsupervised evaluation. The ForgetMe dataset encompasses a diverse set of real and synthetic scenarios, including CUB-200-2011 (Birds), Stanford-Dogs, ImageNet, and a synthetic cat dataset. We apply LoRA fine-tuning on Stable Diffusion to achieve selective unlearning on this dataset and validate the effectiveness of both the ForgetMe dataset and the Entangled metric, establishing them as benchmarks for selective unlearning. Our work provides a scalable and adaptable solution for advancing privacy-preserving generative AI.