MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models

• URL: http://arxiv.org/abs/2602.23798v1
• Date: Fri, 27 Feb 2026 08:39:36 GMT
• Title: MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models
• Authors: Tiantong Wang, Xinyu Yan, Tiantong Wu, Yurong Hao, Yong Jiang, Fei Huang, Wei Yang Bryan Lim,
• Abstract summary: MPU is an algorithm-agnostic privacy-preserving Multiple Perturbed Copies Unlearning framework.<n>We show MPU achieves comparable unlearning performance to noise-free baselines.
• Score: 35.51039829956271
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Machine unlearning for large language models often faces a privacy dilemma in which strict constraints prohibit sharing either the server's parameters or the client's forget set. To address this dual non-disclosure constraint, we propose MPU, an algorithm-agnostic privacy-preserving Multiple Perturbed Copies Unlearning framework that primarily introduces two server-side modules: Pre-Process for randomized copy generation and Post-Process for update aggregation. In Pre-Process, the server distributes multiple perturbed and reparameterized model instances, allowing the client to execute unlearning locally on its private forget set without accessing the server's exact original parameters. After local unlearning, the server performs Post-Process by inverting the reparameterization and aggregating updates with a harmonic denoising procedure to alleviate the impact of perturbation. Experiments with seven unlearning algorithms show that MPU achieves comparable unlearning performance to noise-free baselines, with most algorithms' average degradation well below 1% under 10% noise, and can even outperform the noise-free baseline for some algorithms under 1% noise. Code is available at https://github.com/Tristan-SHU/MPU.

Related papers

• Efficient Federated Unlearning under Plausible Deniability [1.795561427808824]
  Machine unlearning addresses this by modifying the ML parameters in order to forget the influence of a specific data point on its weights. Recent literature has highlighted that the contribution from data point(s) can be forged with some other data points in the dataset with probability close to one. This paper introduces an efficient way to achieve federated unlearning, by employing a privacy model which allows the FL server to plausibly deny the client's participation.
  arXiv  Detail & Related papers  (2024-10-13T18:08:24Z)
• Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning [21.27813247914949]
  We propose Robust-HDP, which efficiently estimates the true noise level in clients model updates.<n>It improves utility and convergence speed, while being safe to the clients that may maliciously send falsified privacy parameter to server.
  arXiv  Detail & Related papers  (2024-06-05T17:41:42Z)
• Advancing the Robustness of Large Language Models through Self-Denoised Smoothing [50.54276872204319]
  Large language models (LLMs) have achieved significant success, but their vulnerability to adversarial perturbations has raised considerable concerns. We propose to leverage the multitasking nature of LLMs to first denoise the noisy inputs and then to make predictions based on these denoised versions. Unlike previous denoised smoothing techniques in computer vision, which require training a separate model to enhance the robustness of LLMs, our method offers significantly better efficiency and flexibility.
  arXiv  Detail & Related papers  (2024-04-18T15:47:00Z)
• Adaptive Differential Privacy in Federated Learning: A Priority-Based Approach [0.0]
  Federated learning (FL) develops global models without direct access to local datasets. DP offers a framework that gives a privacy guarantee by adding certain amounts of noise to parameters. We propose adaptive noise addition in FL which decides the value of injected noise based on features' relative importance.
  arXiv  Detail & Related papers  (2024-01-04T03:01:15Z)
• Just One Byte (per gradient): A Note on Low-Bandwidth Decentralized Language Model Finetuning Using Shared Randomness [86.61582747039053]
  Language model training in distributed settings is limited by the communication cost of exchanges. We extend recent work using shared randomness to perform distributed fine-tuning with low bandwidth.
  arXiv  Detail & Related papers  (2023-06-16T17:59:51Z)
• On Differential Privacy for Federated Learning in Wireless Systems with Multiple Base Stations [90.53293906751747]
  We consider a federated learning model in a wireless system with multiple base stations and inter-cell interference. We show the convergence behavior of the learning process by deriving an upper bound on its optimality gap. Our proposed scheduler improves the average accuracy of the predictions compared with a random scheduler.
  arXiv  Detail & Related papers  (2022-08-25T03:37:11Z)
• FLVoogd: Robust And Privacy Preserving Federated Learning [12.568409209047505]
  We proposeoogd, an updated federated learning method in which servers and clients collaboratively eliminate Byzantine attacks while preserving privacy. Servers use automatic Density-based Spatial Clustering of Applications with Noise (DBSCAN) combined with S2PC to cluster the benign majority without acquiring sensitive personal information. Our framework is automatic and adaptive that servers/clients don't need to tune the parameters during the training.
  arXiv  Detail & Related papers  (2022-06-24T08:48:15Z)
• Corella: A Private Multi Server Learning Approach based on Correlated Queries [30.3330177204504]
  We propose $textitCorella$ as an alternative approach to protect the privacy of data. The proposed scheme relies on a cluster of servers, where at most $T in mathbbN$ of them may collude, each running a learning model. The variance of the noise is set to be large enough to make the information leakage to any subset of up to $T$ servers information-theoretically negligible.
  arXiv  Detail & Related papers  (2020-03-26T17:44:00Z)
• Joint Parameter-and-Bandwidth Allocation for Improving the Efficiency of Partitioned Edge Learning [73.82875010696849]
  Machine learning algorithms are deployed at the network edge for training artificial intelligence (AI) models. This paper focuses on the novel joint design of parameter (computation load) allocation and bandwidth allocation.
  arXiv  Detail & Related papers  (2020-03-10T05:52:15Z)
• User-Level Privacy-Preserving Federated Learning: Analysis and Performance Optimization [77.43075255745389]
  Federated learning (FL) is capable of preserving private data from mobile terminals (MTs) while training the data into useful models. From a viewpoint of information theory, it is still possible for a curious server to infer private information from the shared models uploaded by MTs. We propose a user-level differential privacy (UDP) algorithm by adding artificial noise to the shared models before uploading them to servers.
  arXiv  Detail & Related papers  (2020-02-29T10:13:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.