Differentially Private Fine-Tuning of Diffusion Models

• URL: http://arxiv.org/abs/2406.01355v1
• Date: Mon, 3 Jun 2024 14:18:04 GMT
• Title: Differentially Private Fine-Tuning of Diffusion Models
• Authors: Yu-Lin Tsai, Yizhe Li, Zekai Chen, Po-Yu Chen, Chia-Mu Yu, Xuebin Ren, Francois Buet-Golfouse,
• Abstract summary: 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.
• Score: 22.454127503937883
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential privacy offers a rigorous framework for safeguarding individual data points during model training, with Differential Privacy Stochastic Gradient Descent (DP-SGD) being a prominent implementation. Diffusion method decomposes image generation into iterative steps, theoretically aligning well with DP's incremental noise addition. Despite the natural fit, the unique architecture of DMs necessitates tailored approaches to effectively balance privacy-utility trade-off. Recent developments in this field have highlighted the potential for generating high-quality synthetic data by pre-training on public data (i.e., ImageNet) and fine-tuning on private data, however, there is a pronounced gap in research on optimizing the trade-offs involved in DP settings, particularly concerning parameter efficiency and model scalability. Our work addresses this by proposing a parameter-efficient fine-tuning strategy optimized for private diffusion models, which minimizes the number of trainable parameters to enhance the privacy-utility trade-off. We empirically demonstrate that our method achieves state-of-the-art performance in DP synthesis, significantly surpassing previous benchmarks on widely studied datasets (e.g., with only 0.47M trainable parameters, achieving a more than 35% improvement over the previous state-of-the-art with a small privacy budget on the CelebA-64 dataset). Anonymous codes available at https://anonymous.4open.science/r/DP-LORA-F02F.

Related papers

• Pseudo-Probability Unlearning: Towards Efficient and Privacy-Preserving Machine Unlearning [59.29849532966454]
  We propose PseudoProbability Unlearning (PPU), a novel method that enables models to forget data to adhere to privacy-preserving manner. Our method achieves over 20% improvements in forgetting error compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-11-04T21:27:06Z)
• Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training [10.229653770070202]
  Training generative models with differential privacy (DP) typically involves injecting noise into gradient updates or adapting the discriminator's training procedure. We consider the slicing privacy mechanism that injects noise into random low-dimensional projections of the private data. We present a kernel-based estimator for this divergence, circumventing the need for adversarial training.
  arXiv  Detail & Related papers  (2024-10-25T19:32:58Z)
• 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)
• Pre-training Differentially Private Models with Limited Public Data [54.943023722114134]
  differential privacy (DP) is a prominent method to gauge the degree of security provided to the models. DP is yet not capable of protecting a substantial portion of the data used during the initial pre-training stage. We develop a novel DP continual pre-training strategy using only 10% of public data. Our strategy can achieve DP accuracy of 41.5% on ImageNet-21k, as well as non-DP accuracy of 55.7% and and 60.0% on downstream tasks Places365 and iNaturalist-2021.
  arXiv  Detail & Related papers  (2024-02-28T23:26:27Z)
• DPGOMI: Differentially Private Data Publishing with Gaussian Optimized Model Inversion [8.204115285718437]
  We propose Differentially Private Data Publishing with Gaussian Optimized Model Inversion (DPGOMI) to address this issue. Our approach involves mapping private data to the latent space using a public generator, followed by a lower-dimensional DP-GAN with better convergence properties. Our results show that DPGOMI outperforms the standard DP-GAN method in terms of Inception Score, Freche't Inception Distance, and classification performance.
  arXiv  Detail & Related papers  (2023-10-06T18:46:22Z)
• 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)
• Just Fine-tune Twice: Selective Differential Privacy for Large Language Models [69.66654761324702]
  We propose a simple yet effective just-fine-tune-twice privacy mechanism to achieve SDP for large Transformer-based language models. Experiments show that our models achieve strong performance while staying robust to the canary insertion attack.
  arXiv  Detail & Related papers  (2022-04-15T22:36:55Z)
• 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)
• PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning [1.8692254863855962]
  We propose a new framework of data using deep generative models in a differentially private manner. Within our framework, sensitive data are sanitized with rigorous privacy guarantees in a one-shot fashion. Our proposal has theoretical guarantees of performance, and empirical evaluations on multiple datasets show that our approach outperforms other methods at reasonable levels of privacy.
  arXiv  Detail & Related papers  (2021-06-08T18:00:01Z)
• 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.