paper-with-me

Papers

Differentially Private Fine-Tuning of Diffusion Models

2024-06-03 · Yu-Lin Tsai, Yizhe Li, Zekai Chen, Po-Yu Chen, Chia-Mu Yu, Xuebin Ren, Francois Buet-Golfouse

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.

📄 PDF Abstract BibTeX arXiv:2406.01355

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationMemorizationparameter-efficient fine-tuning

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning

2024-03-21 · Jonathan Lebensold, Maziar Sanjabi, Pietro Astolfi, Adriana Romero-Soriano 외

Text-to-image diffusion models have been shown to suffer from sample-level memorization, possibly reproducing near-perfect replica of images that they are trained on, which may be undesirable. To remedy this issue, we de…

MemorizationRetrievalRetrieval-augmented Generation

Efficient Differentially Private Fine-Tuning of Diffusion Models

2024-06-07 · Jing Liu, Andrew Lowy, Toshiaki Koike-Akino, Kieran Parsons 외

The recent developments of Diffusion Models (DMs) enable generation of astonishingly high-quality synthetic samples. Recent work showed that the synthetic samples generated by the diffusion model, which is pre-trained on…

parameter-efficient fine-tuning

Differentially Private Adaptation of Diffusion Models via Noisy Aggregated Embeddings

2024-11-22 · Pura Peetathawatchai, Wei-Ning Chen, Berivan Isik, Sanmi Koyejo 외

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 p…

Privacy PreservingStyle Transfer

Differentially Private Fine-tuning of Language Models

2021-10-13 · ICLR 2022 4 · Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi 외

We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-scale pre-trained language models, which achieve the state-of-the-art privacy versus utility tradeoffs on many standard NLP …

Text Generation

Differentially Private Diffusion Models Generate Useful Synthetic Images

2023-02-27 · Sahra Ghalebikesabi, Leonard Berrada, Sven Gowal, Ira Ktena 외

The ability to generate privacy-preserving synthetic versions of sensitive image datasets could unlock numerous ML applications currently constrained by data availability. Due to their astonishing image generation qualit…

Image GenerationPrivacy Preserving