Differentially Private Adaptation of Diffusion Models via Noisy Aggregated Embeddings

• URL: http://arxiv.org/abs/2411.14639v2
• Date: Mon, 24 Feb 2025 19:31:01 GMT
• Title: Differentially Private Adaptation of Diffusion Models via Noisy Aggregated Embeddings
• Authors: Pura Peetathawatchai, Wei-Ning Chen, Berivan Isik, Sanmi Koyejo, Albert No,
• Abstract summary: We introduce a novel method for adapting diffusion models under differential privacy constraints.<n>This method enables privacy-preserving style and content transfer without fine-tuning model weights.<n> Experimental results show that the TI-based adaptation achieves superior fidelity in style transfer, even under strong privacy guarantees.
• Score: 23.687702204151872
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce a novel method for adapting diffusion models under differential privacy (DP) constraints, enabling privacy-preserving style and content transfer without fine-tuning model weights. Traditional approaches to private adaptation, such as DP-SGD, incur significant computational and memory overhead when applied to large, complex models. In addition, when adapting to small-scale specialized datasets, DP-SGD incurs large amount of noise that significantly degrades the performance. Our approach instead leverages an embedding-based technique derived from Textual Inversion (TI) and adapted with differentially private mechanisms. We apply TI to Stable Diffusion for style adaptation using two private datasets: a collection of artworks by a single artist and pictograms from the Paris 2024 Olympics. Experimental results show that the TI-based adaptation achieves superior fidelity in style transfer, even under strong privacy guarantees.

Related papers

• An Optimization Framework for Differentially Private Sparse Fine-Tuning [24.545715091775488]
  Differentially private gradient descent (DP-SGD) is broadly considered to be the gold standard for training and fine-tuning neural networks under differential privacy (DP) Recent work has shown that privately fine-tuning only a small subset of model weights and keeping the rest of the weights fixed can lead to better performance. In this work, we propose a new approach for sparse fine-tuning of neural networks under DP.
  arXiv  Detail & Related papers  (2025-03-17T05:05:05Z)
• Masked Differential Privacy [64.32494202656801]
  We propose an effective approach called masked differential privacy (DP), which allows for controlling sensitive regions where differential privacy is applied. Our method operates selectively on data and allows for defining non-sensitive-temporal regions without DP application or combining differential privacy with other privacy techniques within data samples.
  arXiv  Detail & Related papers  (2024-10-22T15:22:53Z)
• Privacy-preserving datasets by capturing feature distributions with Conditional VAEs [0.11999555634662634]
  Conditional Variational Autoencoders (CVAEs) trained on feature vectors extracted from large pre-trained vision foundation models. Our method notably outperforms traditional approaches in both medical and natural image domains. Results underscore the potential of generative models to significantly impact deep learning applications in data-scarce and privacy-sensitive environments.
  arXiv  Detail & Related papers  (2024-08-01T15:26:24Z)
• Model Inversion Attacks Through Target-Specific Conditional Diffusion Models [54.69008212790426]
  Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MIAs tend to suffer from inferior generative fidelity due to GAN's inherent flaws and biased optimization within latent space. We propose Diffusion-based Model Inversion (Diff-MI) attacks to alleviate these issues.
  arXiv  Detail & Related papers  (2024-07-16T06:38:49Z)
• 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)
• Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation [59.184980778643464]
  Fine-tuning Diffusion Models remains an underexplored frontier in generative artificial intelligence (GenAI) In this paper, we introduce an innovative technique called self-play fine-tuning for diffusion models (SPIN-Diffusion) Our approach offers an alternative to conventional supervised fine-tuning and RL strategies, significantly improving both model performance and alignment.
  arXiv  Detail & Related papers  (2024-02-15T18:59:18Z)
• Sparsity-Preserving Differentially Private Training of Large Embedding Models [67.29926605156788]
  DP-SGD is a training algorithm that combines differential privacy with gradient descent. Applying DP-SGD naively to embedding models can destroy gradient sparsity, leading to reduced training efficiency. We present two new algorithms, DP-FEST and DP-AdaFEST, that preserve gradient sparsity during private training of large embedding models.
  arXiv  Detail & Related papers  (2023-11-14T17:59:51Z)
• DP-Mix: Mixup-based Data Augmentation for Differentially Private Learning [10.971246386083884]
  We propose two novel data augmentation techniques specifically designed for the constraints of differentially private learning. Our first technique, DP-Mix_Self, achieves SoTA classification performance across a range of datasets and settings by performing mixup on self-augmented data. Our second technique, DP-Mix_Diff, further improves performance by incorporating synthetic data from a pre-trained diffusion model into the mixup process.
  arXiv  Detail & Related papers  (2023-11-02T15:12:12Z)
• A Novel Cross-Perturbation for Single Domain Generalization [54.612933105967606]
  Single domain generalization aims to enhance the ability of the model to generalize to unknown domains when trained on a single source domain. The limited diversity in the training data hampers the learning of domain-invariant features, resulting in compromised generalization performance. We propose CPerb, a simple yet effective cross-perturbation method to enhance the diversity of the training data.
  arXiv  Detail & Related papers  (2023-08-02T03:16:12Z)
• DP-TBART: A Transformer-based Autoregressive Model for Differentially Private Tabular Data Generation [1.4418363806859886]
  We present Differentially-Private TaBular AutoRegressive Transformer (DP-TBART), a transformer-based autoregressive model that maintains differential privacy. We provide a theoretical framework for understanding the limitations of marginal-based approaches and where deep learning-based approaches stand to contribute most.
  arXiv  Detail & Related papers  (2023-07-19T19:40:21Z)
• FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations [53.268801169075836]
  We propose FedLAP-DP, a novel privacy-preserving approach for federated learning. A formal privacy analysis demonstrates that FedLAP-DP incurs the same privacy costs as typical gradient-sharing schemes. Our approach presents a faster convergence speed compared to typical gradient-sharing methods.
  arXiv  Detail & Related papers  (2023-02-02T12:56:46Z)
• Private Set Generation with Discriminative Information [63.851085173614]
  Differentially private data generation is a promising solution to the data privacy challenge. Existing private generative models are struggling with the utility of synthetic samples. We introduce a simple yet effective method that greatly improves the sample utility of state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-11-07T10:02:55Z)
• On the utility and protection of optimization with differential privacy and classic regularization techniques [9.413131350284083]
  We study the effectiveness of the differentially-private descent (DP-SGD) algorithm against standard optimization practices with regularization techniques. We discuss differential privacy's flaws and limits and empirically demonstrate the often superior privacy-preserving properties of dropout and l2-regularization.
  arXiv  Detail & Related papers  (2022-09-07T14:10:21Z)
• Large Scale Transfer Learning for Differentially Private Image Classification [51.10365553035979]
  Differential Privacy (DP) provides a formal framework for training machine learning models with individual example level privacy. Private training using DP-SGD protects against leakage by injecting noise into individual example gradients. While this result is quite appealing, the computational cost of training large-scale models with DP-SGD is substantially higher than non-private training.
  arXiv  Detail & Related papers  (2022-05-06T01:22:20Z)
• Differentially Private Generative Adversarial Networks with Model Inversion [6.651002556438805]
  To protect sensitive data in training a Generative Adversarial Network (GAN), the standard approach is to use differentially private (DP) gradient descent method. We propose Differentially Private Model Inversion (DPMI) method where the private data is first mapped to the latent space via a public generator. Our approach outperforms the standard DP-GAN method based on Inception Score, Fr'echet Inception Distance, and classification accuracy under the same privacy guarantee.
  arXiv  Detail & Related papers  (2022-01-10T02:26:26Z)
• Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence [73.14373832423156]
  We propose DP-Sinkhorn, a novel optimal transport-based generative method for learning data distributions from private data with differential privacy. Unlike existing approaches for training differentially private generative models, we do not rely on adversarial objectives.
  arXiv  Detail & Related papers  (2021-11-01T18:10:21Z)
• Large Language Models Can Be Strong Differentially Private Learners [70.0317718115406]
  Differentially Private (DP) learning has seen limited success for building large deep learning models of text. We show that this performance drop can be mitigated with the use of large pretrained models. We propose a memory saving technique that allows clipping in DP-SGD to run without instantiating per-example gradients.
  arXiv  Detail & Related papers  (2021-10-12T01:45:27Z)
• DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation [15.63770709526671]
  We propose a scalable privacy-preserving generative model DATALENS. We show that, DATALENS significantly outperforms other baseline DP generative models. We adapt the proposed TOPAGG approach, which is one of the key building blocks in DATALENS, to DP SGD training.
  arXiv  Detail & Related papers  (2021-03-20T06:14:19Z)
• 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)

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.