# Fully Decentralized Certified Unlearning

arXiv: https://arxiv.org/abs/2512.08443 · HTML: https://mlsanity.com/paper/2512.08443/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 32 of its 52 references that are in the map.
- First posted on arXiv 9 Dec 2025.

## Placed in

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

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [A Unified Theory of Decentralized SGD with Changing Topology and Local Updates](https://mlsanity.com/paper/2003.10422/) (2020)
- [Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences](https://mlsanity.com/paper/1807.01647/) (2018)
- [Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity](https://mlsanity.com/paper/1811.12469/) (2018)
- [Asynchronous Decentralized Parallel Stochastic Gradient Descent](https://mlsanity.com/paper/1710.06952/) (2017)
- [Privacy Amplification by Iteration](https://mlsanity.com/paper/1808.06651/) (2018)
- [Federated Unlearning: How to Efficiently Erase a Client in FL?](https://mlsanity.com/paper/2207.05521/) (2022)
- [The Privacy Blanket of the Shuffle Model](https://mlsanity.com/paper/1903.02837/) (2019)
- [A Survey on Federated Unlearning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/2310.20448/) (2023)
- [Forget Unlearning: Towards True Data-Deletion in Machine Learning](https://mlsanity.com/paper/2210.08911/) (2022)
- [Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning](https://mlsanity.com/paper/2401.10371/) (2024)
- [Decentralized gradient methods: does topology matter?](https://mlsanity.com/paper/2002.12688/) (2020)
- [Towards Certified Unlearning for Deep Neural Networks](https://mlsanity.com/paper/2408.00920/) (2024)
- [Certified Unlearning for Neural Networks](https://mlsanity.com/paper/2506.06985/) (2025)
- [Gossip Dual Averaging for Decentralized Optimization of Pairwise Functions](https://mlsanity.com/paper/1606.02421/) (2016)
- [The Utility and Complexity of in- and out-of-Distribution Machine Unlearning](https://mlsanity.com/paper/2412.09119/) (2024)
- [Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions](https://mlsanity.com/paper/2409.09778/) (2024)
- [Tight Bounds for Machine Unlearning via Differential Privacy](https://mlsanity.com/paper/2309.00886/) (2023)
- [Communication Efficient and Provable Federated Unlearning](https://mlsanity.com/paper/2401.11018/) (2024)
- [The Privacy Power of Correlated Noise in Decentralized Learning](https://mlsanity.com/paper/2405.01031/) (2024)
- [Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learning](https://mlsanity.com/paper/2304.10638/) (2023)
- [Differentially Private Summation with Multi-Message Shuffling](https://mlsanity.com/paper/1906.09116/) (2019)
- [When to Forget? Complexity Trade-offs in Machine Unlearning](https://mlsanity.com/paper/2502.17323/) (2025)

## Built on by (most cited first, 1 of 1)

- [Priority-Aware Learning-Unlearning Correction for Dynamic Decentralized LoRA Fine-Tuning](https://mlsanity.com/paper/2606.22878/) (2026)

## Abstract (arXiv)

Machine unlearning (MU) seeks to remove the influence of specified data from a trained model in response to privacy requests or data poisoning. While certified unlearning has been analyzed in centralized and server-orchestrated federated settings (via guarantees analogous to differential privacy, DP), the decentralized setting -- where peers communicate without a coordinator remains underexplored. We study certified unlearning in decentralized networks with fixed topologies and propose RR-DU, a random-walk procedure that performs one projected gradient ascent step on the forget set at the unlearning client and a geometrically distributed number of projected descent steps on the retained data elsewhere, combined with subsampled Gaussian noise and projection onto a trust region around the original model. We provide (i) convergence guarantees in the convex case and stationarity guarantees in the nonconvex case, (ii) (varepsilon,δ) network-unlearning certificates on client views via subsampled Gaussian R'enyi DP (RDP) with segment-level subsampling, and (iii) deletion-capacity bounds that scale with the forget-to-local data ratio and quantify the effect of decentralization (network mixing and randomized subsampling) on the privacy-utility trade-off. Empirically, on image benchmarks (MNIST, CIFAR-10), RR-DU matches a given (varepsilon,δ) while achieving higher test accuracy than decentralized DP baselines and reducing forget accuracy to random guessing (≈ 10%).