# FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learning

arXiv: https://arxiv.org/abs/2309.10283 · HTML: https://mlsanity.com/paper/2309.10283/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security.
- Builds on 29 of its 67 references that are in the map.
- First posted on arXiv 19 Sep 2023.

## Placed in

- LLM safety and security / [Federated unlearning and poisoning](https://mlsanity.com/safety/federated-unlearning-and-poisoning/)

## Builds on (most cited first, 29 of 29)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection](https://mlsanity.com/paper/1907.09693/) (2019)
- [Multimodal Deep Learning](https://mlsanity.com/paper/2301.04856/) (2023)
- [Federated Learning for Smart Healthcare: A Survey](https://mlsanity.com/paper/2111.08834/) (2021)
- [Zero-Shot Machine Unlearning](https://mlsanity.com/paper/2201.05629/) (2022)
- [A review: Deep learning for medical image segmentation using multi-modality fusion](https://mlsanity.com/paper/2004.10664/) (2020)
- [Privacy Preserving Machine Learning: Threats and Solutions](https://mlsanity.com/paper/1804.11238/) (2018)
- [A General Survey on Attention Mechanisms in Deep Learning](https://mlsanity.com/paper/2203.14263/) (2022)
- [CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning](https://mlsanity.com/paper/2303.03323/) (2023)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)
- [Survey: Leakage and Privacy at Inference Time](https://mlsanity.com/paper/2107.01614/) (2021)
- [Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning](https://mlsanity.com/paper/2302.02069/) (2023)
- [A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and Comparison](https://mlsanity.com/paper/2110.10223/) (2021)
- [Deep Attention Recurrent Q-Network](https://mlsanity.com/paper/1512.01693/) (2015)
- [More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence](https://mlsanity.com/paper/2008.01916/) (2020)
- [Privacy Enhanced Multimodal Neural Representations for Emotion Recognition](https://mlsanity.com/paper/1910.13212/) (2019)
- [A better measure of relative prediction accuracy for model selection and model estimation](https://mlsanity.com/paper/2105.05249/) (2021)
- [FedStack: Personalized activity monitoring using stacked federated learning](https://mlsanity.com/paper/2209.13080/) (2022)
- [Graph-enabled Reinforcement Learning for Time Series Forecasting with Adaptive Intelligence](https://mlsanity.com/paper/2309.10186/) (2023)
- [Model-Protected Multi-Task Learning](https://mlsanity.com/paper/1809.06546/) (2018)
- [Unfolded Self-Reconstruction LSH: Towards Machine Unlearning in Approximate Nearest Neighbour Search](https://mlsanity.com/paper/2304.02350/) (2023)

## Built on by (most cited first, 13 of 13)

- [A Survey on Federated Unlearning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/2310.20448/) (2023)
- [Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics](https://mlsanity.com/paper/2401.05146/) (2024)
- [A Survey on Safe Multi-Modal Learning System](https://mlsanity.com/paper/2402.05355/) (2024)
- [Privacy-R1: Privacy-Aware Multi-LLM Agent Collaboration via Reinforcement Learning](https://mlsanity.com/paper/2510.16054/) (2025)
- [Adaptive Multi-Agent Deep Reinforcement Learning for Timely Healthcare Interventions](https://mlsanity.com/paper/2309.10980/) (2023)
- [LetheViT: Selective Machine Unlearning for Vision Transformers via Attention-Guided Contrastive Learning](https://mlsanity.com/paper/2508.01569/) (2025)
- [Model Inversion Attack against Federated Unlearning](https://mlsanity.com/paper/2502.14558/) (2025)
- [Exploring Incremental Unlearning: Techniques, Challenges, and Future Directions](https://mlsanity.com/paper/2502.16708/) (2025)
- [Rethinking Federated Unlearning via the Lens of Memorization](https://mlsanity.com/paper/2605.24545/) (2026)
- [A Survey on Federated Unlearning: Challenges and Opportunities](https://mlsanity.com/paper/2403.02437/) (2024)
- [Beyond Right to be Forgotten: Managing Heterogeneity Side Effects Through Strategic Incentives](https://mlsanity.com/paper/2410.15045/) (2024)
- [DRAUN: An Algorithm-Agnostic Data Reconstruction Attack on Federated Unlearning Systems](https://mlsanity.com/paper/2506.01777/) (2025)
- [Hierarchical Dual-Strategy Unlearning for Biomedical and Healthcare Intelligence Using Imperfect and Privacy-Sensitive Medical Data](https://mlsanity.com/paper/2511.19498/) (2025)

## Abstract (arXiv)

Machine Unlearning is an emerging field that addresses data privacy issues by enabling the removal of private or irrelevant data from the Machine Learning process. Challenges related to privacy and model efficiency arise from the use of outdated, private, and irrelevant data. These issues compromise both the accuracy and the computational efficiency of models in both Machine Learning and Unlearning. To mitigate these challenges, we introduce a novel framework, Attention-based Machine Unlearning using Federated Reinforcement Learning (FRAMU). This framework incorporates adaptive learning mechanisms, privacy preservation techniques, and optimization strategies, making it a well-rounded solution for handling various data sources, either single-modality or multi-modality, while maintaining accuracy and privacy. FRAMU's strength lies in its adaptability to fluctuating data landscapes, its ability to unlearn outdated, private, or irrelevant data, and its support for continual model evolution without compromising privacy. Our experiments, conducted on both single-modality and multi-modality datasets, revealed that FRAMU significantly outperformed baseline models. Additional assessments of convergence behavior and optimization strategies further validate the framework's utility in federated learning applications. Overall, FRAMU advances Machine Unlearning by offering a robust, privacy-preserving solution that optimizes model performance while also addressing key challenges in dynamic data environments.