# PDLRecover: Privacy-preserving Decentralized Model Recovery with Machine Unlearning

arXiv: https://arxiv.org/abs/2506.15112 · HTML: https://mlsanity.com/paper/2506.15112/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 28 of its 39 references that are in the map.
- First posted on arXiv 18 Jun 2025.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 28 of 28)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (2018)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [Local Model Poisoning Attacks to Byzantine-Robust Federated Learning](https://mlsanity.com/paper/1911.11815/) (2019)
- [New insights and perspectives on the natural gradient method](https://mlsanity.com/paper/1412.1193/) (2014)
- [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://mlsanity.com/paper/2101.05930/) (2021)
- [When Machine Unlearning Jeopardizes Privacy](https://mlsanity.com/paper/2005.02205/) (2020)
- [Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses](https://mlsanity.com/paper/2012.10544/) (2020)
- [On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning](https://mlsanity.com/paper/2110.11891/) (2021)
- [DeltaGrad: Rapid retraining of machine learning models](https://mlsanity.com/paper/2006.14755/) (2020)
- [Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges](https://mlsanity.com/paper/2211.08413/) (2022)
- [Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness](https://mlsanity.com/paper/2005.00060/) (2020)
- [SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics](https://mlsanity.com/paper/2104.11315/) (2021)
- [Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection](https://mlsanity.com/paper/1908.00686/) (2019)
- [The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining](https://mlsanity.com/paper/2203.07320/) (2022)
- [BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning](https://mlsanity.com/paper/1905.06731/) (2019)
- [Machine Unlearning: Solutions and Challenges](https://mlsanity.com/paper/2308.07061/) (2023)
- [Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff](https://mlsanity.com/paper/2011.09527/) (2020)
- [Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models](https://mlsanity.com/paper/2310.13828/) (2023)
- [Federated Unlearning with Knowledge Distillation](https://mlsanity.com/paper/2201.09441/) (2022)
- [FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information](https://mlsanity.com/paper/2210.10936/) (2022)
- [A Multi-Batch L-BFGS Method for Machine Learning](https://mlsanity.com/paper/1605.06049/) (2016)
- [Poison Attack and Defense on Deep Source Code Processing Models](https://mlsanity.com/paper/2210.17029/) (2022)
- [Hessian Eigenvectors and Principal Component Analysis of Neural Network Weight Matrices](https://mlsanity.com/paper/2311.00452/) (2023)
- [Data Poisoning Attacks on EEG Signal-based Risk Assessment Systems](https://mlsanity.com/paper/2302.04224/) (2023)

## Abstract (arXiv)

Decentralized learning is vulnerable to poison attacks, where malicious clients manipulate local updates to degrade global model performance. Existing defenses mainly detect and filter malicious models, aiming to prevent a limited number of attackers from corrupting the global model. However, restoring an already compromised global model remains a challenge. A direct approach is to remove malicious clients and retrain the model using only the benign clients. Yet, retraining is time-consuming, computationally expensive, and may compromise model consistency and privacy. We propose PDLRecover, a novel method to recover a poisoned global model efficiently by leveraging historical model information while preserving privacy. The main challenge lies in protecting shared historical models while enabling parameter estimation for model recovery. By exploiting the linearity of approximate Hessian matrix computation, we apply secret sharing to protect historical updates, ensuring local models are not leaked during transmission or reconstruction. PDLRecover introduces client-side preparation, periodic recovery updates, and a final exact update to ensure robustness and convergence of the recovered model. Periodic updates maintain accurate curvature information, and the final step ensures high-quality convergence. Experiments show that the recovered global model achieves performance comparable to a fully retrained model but with significantly reduced computation and time cost. Moreover, PDLRecover effectively prevents leakage of local model parameters, ensuring both accuracy and privacy in recovery.