Extracting Training Data from Diffusion Models
- URL: http://arxiv.org/abs/2301.13188v1
- Date: Mon, 30 Jan 2023 18:53:09 GMT
- Title: Extracting Training Data from Diffusion Models
- Authors: Nicholas Carlini, Jamie Hayes, Milad Nasr, Matthew Jagielski, Vikash
Sehwag, Florian Tram\`er, Borja Balle, Daphne Ippolito, Eric Wallace
- Abstract summary: We show that diffusion models memorize individual images from their training data and emit them at generation time.
With a generate-and-filter pipeline, we extract over a thousand training examples from state-of-the-art models.
We train hundreds of diffusion models in various settings to analyze how different modeling and data decisions affect privacy.
- Score: 77.11719063152027
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion have
attracted significant attention due to their ability to generate high-quality
synthetic images. In this work, we show that diffusion models memorize
individual images from their training data and emit them at generation time.
With a generate-and-filter pipeline, we extract over a thousand training
examples from state-of-the-art models, ranging from photographs of individual
people to trademarked company logos. We also train hundreds of diffusion models
in various settings to analyze how different modeling and data decisions affect
privacy. Overall, our results show that diffusion models are much less private
than prior generative models such as GANs, and that mitigating these
vulnerabilities may require new advances in privacy-preserving training.
Related papers
- DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception [66.88792390480343]
We propose DEEM, a simple and effective approach that utilizes the generative feedback of diffusion models to align the semantic distributions of the image encoder.
DEEM exhibits enhanced robustness and a superior capacity to alleviate hallucinations while utilizing fewer trainable parameters, less pre-training data, and a smaller base model size.
arXiv Detail & Related papers (2024-05-24T05:46:04Z) - Diffusion Models Trained with Large Data Are Transferable Visual Models [49.84679952948808]
We show that it is possible to achieve remarkable transferable performance on fundamental vision perception tasks using a moderate amount of target data.
Results showcase the remarkable transferability of the backbone of diffusion models across diverse tasks and real-world datasets.
arXiv Detail & Related papers (2024-03-10T04:23:24Z) - Large-scale Reinforcement Learning for Diffusion Models [30.164571425479824]
Text-to-image diffusion models are susceptible to implicit biases that arise from web-scale text-image training pairs.
We present an effective scalable algorithm to improve diffusion models using Reinforcement Learning (RL)
We show how our approach substantially outperforms existing methods for aligning diffusion models with human preferences.
arXiv Detail & Related papers (2024-01-20T08:10:43Z) - Conditional Image Generation with Pretrained Generative Model [1.4685355149711303]
diffusion models have gained popularity for their ability to generate higher-quality images in comparison to GAN models.
These models require a huge amount of data, computational resources, and meticulous tuning for successful training.
We propose methods to leverage pre-trained unconditional diffusion models with additional guidance for the purpose of conditional image generative.
arXiv Detail & Related papers (2023-12-20T18:27:53Z) - Diffusion Cocktail: Fused Generation from Diffusion Models [8.307057730976432]
Diffusion models excel at generating high-quality images and are easy to extend.
Recent work has focused on uncovering semantic and visual information encoded in various components of a diffusion model.
We propose Diffusion Cocktail (Ditail), a training-free method that can accurately transfer content information between two diffusion models.
arXiv Detail & Related papers (2023-12-12T00:53:56Z) - Generating images of rare concepts using pre-trained diffusion models [32.5337654536764]
Text-to-image diffusion models can synthesize high-quality images, but they have various limitations.
We show that their limitation is partly due to the long-tail nature of their training data.
We show that rare concepts can be correctly generated by carefully selecting suitable generation seeds in the noise space.
arXiv Detail & Related papers (2023-04-27T20:55:38Z) - Diffusion Models as Masked Autoencoders [52.442717717898056]
We revisit generatively pre-training visual representations in light of recent interest in denoising diffusion models.
While directly pre-training with diffusion models does not produce strong representations, we condition diffusion models on masked input and formulate diffusion models as masked autoencoders (DiffMAE)
We perform a comprehensive study on the pros and cons of design choices and build connections between diffusion models and masked autoencoders.
arXiv Detail & Related papers (2023-04-06T17:59:56Z) - Diffusion Art or Digital Forgery? Investigating Data Replication in
Diffusion Models [53.03978584040557]
We study image retrieval frameworks that enable us to compare generated images with training samples and detect when content has been replicated.
Applying our frameworks to diffusion models trained on multiple datasets including Oxford flowers, Celeb-A, ImageNet, and LAION, we discuss how factors such as training set size impact rates of content replication.
arXiv Detail & Related papers (2022-12-07T18:58:02Z) - SinDiffusion: Learning a Diffusion Model from a Single Natural Image [159.4285444680301]
We present SinDiffusion, leveraging denoising diffusion models to capture internal distribution of patches from a single natural image.
It is based on two core designs. First, SinDiffusion is trained with a single model at a single scale instead of multiple models with progressive growing of scales.
Second, we identify that a patch-level receptive field of the diffusion network is crucial and effective for capturing the image's patch statistics.
arXiv Detail & Related papers (2022-11-22T18:00:03Z)
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.