Nonparametric Variational Differential Privacy via Embedding Parameter Clipping

• URL: http://arxiv.org/abs/2603.09583v2
• Date: Thu, 19 Mar 2026 13:29:29 GMT
• Title: Nonparametric Variational Differential Privacy via Embedding Parameter Clipping
• Abstract summary: We introduce a principled parameter clipping strategy to address privacy issues in variational language models.<n>Our findings show that the clipped model consistently achieves tighter RD bounds, implying stronger privacy.<n>This work presents a simple yet effective method for improving the privacy-utility trade-off in variational models, making them more robust and practical.
• Score: 7.242101014224729
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The nonparametric variational information bottleneck (NVIB) provides the foundation for nonparametric variational differential privacy (NVDP), a framework for building privacy-preserving language models. However, the learned latent representations can drift into regions with high information content, leading to poor privacy guarantees, but also low utility due to numerical instability during training. In this work, we introduce a principled parameter clipping strategy to directly address this issue. Our method is mathematically derived from the objective of minimizing the Rényi Divergence (RD) upper bound, yielding specific, theoretically grounded constraints on the posterior mean, variance, and mixture weight parameters. We apply our technique to an NVIB based model and empirically compare it against an unconstrained baseline. Our findings demonstrate that the clipped model consistently achieves tighter RD bounds, implying stronger privacy, while simultaneously attaining higher performance on several downstream tasks. This work presents a simple yet effective method for improving the privacy-utility trade-off in variational models, making them more robust and practical.

Related papers

• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data [55.84428098924793]
  We propose Constrained Uniform Top-K Sampling (CUTS), a parameter-free decoding strategy enforcing structure-preserving exploration.<n>We integrate this into Mixed-CUTS, a training framework synergizing exploitative and exploratory rollouts to amplify intra-group advantage variance.<n> Notably, Mixed-CUTS improves Pass@1 accuracy on the challenging AIME25 benchmark by up to 15.1% over standard GRPO.
  arXiv  Detail & Related papers  (2026-04-20T16:43:28Z)
• Parameter-Efficient Fine-Tuning with Differential Privacy for Robust Instruction Adaptation in Large Language Models [11.071281023081582]
  This study addresses the issues of privacy protection and efficiency in instruction fine-tuning of large-scale language models.<n>It proposes a parameter-efficient method that integrates differential privacy noise allocation with gradient clipping in a collaborative optimization framework.<n>Results show that the method outperforms baseline models in accuracy, privacy budget, and parameter efficiency, and maintains stable performance under diverse and uncertain data conditions.
  arXiv  Detail & Related papers  (2025-12-07T08:01:01Z)
• Multi-Objective Optimization for Privacy-Utility Balance in Differentially Private Federated Learning [12.278668095136098]
  Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data.<n>We propose an adaptive clipping mechanism that dynamically adjusts the clipping norm using a multi-objective optimization framework.<n>Our results show that adaptive clipping consistently outperforms fixed-clipping baselines, achieving improved accuracy under the same privacy constraints.
  arXiv  Detail & Related papers  (2025-03-27T04:57:05Z)
• Differentially Private Random Feature Model [47.35176457481132]
  We produce a differentially private random feature model for privacy-preserving kernel machines.<n>We show that our method preserves privacy and derive a generalization error bound for the method.
  arXiv  Detail & Related papers  (2024-12-06T05:31:08Z)
• Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models [2.3281513013731145]
  Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. Differential Privacy (DP) offers a solution to mitigate these risks, but introduces significant computational and performance trade-offs. We show that PEFT methods achieve comparable performance to standard fine-tuning while requiring fewer parameters and significantly reducing privacy leakage.
  arXiv  Detail & Related papers  (2024-11-24T13:17:36Z)
• Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation [33.795122935686706]
  We propose ANADP, a novel algorithm that adaptively allocates additive noise based on the importance of model parameters. We demonstrate that ANADP narrows the performance gap between regular fine-tuning and traditional DP fine-tuning on a series of datasets.
  arXiv  Detail & Related papers  (2024-10-03T19:02:50Z)
• Differentially Private Fine-Tuning of Diffusion Models [22.454127503937883]
  The integration of Differential Privacy with diffusion models (DMs) presents a promising yet challenging frontier. Recent developments in this field have highlighted the potential for generating high-quality synthetic data by pre-training on public data. We propose a strategy optimized for private diffusion models, which minimizes the number of trainable parameters to enhance the privacy-utility trade-off.
  arXiv  Detail & Related papers  (2024-06-03T14:18:04Z)
• The Risk of Federated Learning to Skew Fine-Tuning Features and Underperform Out-of-Distribution Robustness [50.52507648690234]
  Federated learning has the risk of skewing fine-tuning features and compromising the robustness of the model. We introduce three robustness indicators and conduct experiments across diverse robust datasets. Our approach markedly enhances the robustness across diverse scenarios, encompassing various parameter-efficient fine-tuning methods.
  arXiv  Detail & Related papers  (2024-01-25T09:18:51Z)
• Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models [109.06052781040916]
  We introduce a technique to enhance the inference efficiency of parameter-shared language models. We also propose a simple pre-training technique that leads to fully or partially shared models. Results demonstrate the effectiveness of our methods on both autoregressive and autoencoding PLMs.
  arXiv  Detail & Related papers  (2023-10-19T15:13:58Z)
• Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness [61.827054365139645]
  Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. We propose an alternative model, DU-VAE, for learning a more Diverse and less Uncertain latent space.
  arXiv  Detail & Related papers  (2021-10-24T07:58:13Z)
• Differentially Private Federated Learning with Laplacian Smoothing [72.85272874099644]
  Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. An adversary may still be able to infer the private training data by attacking the released model. Differential privacy provides a statistical protection against such attacks at the price of significantly degrading the accuracy or utility of the trained models.
  arXiv  Detail & Related papers  (2020-05-01T04:28:38Z)
• Learnable Bernoulli Dropout for Bayesian Deep Learning [53.79615543862426]
  Learnable Bernoulli dropout (LBD) is a new model-agnostic dropout scheme that considers the dropout rates as parameters jointly optimized with other model parameters. LBD leads to improved accuracy and uncertainty estimates in image classification and semantic segmentation.
  arXiv  Detail & Related papers  (2020-02-12T18:57:14Z)

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.