Extracting Training Data from Unconditional Diffusion Models
- URL: http://arxiv.org/abs/2406.12752v1
- Date: Tue, 18 Jun 2024 16:20:12 GMT
- Title: Extracting Training Data from Unconditional Diffusion Models
- Authors: Yunhao Chen, Xingjun Ma, Difan Zou, Yu-Gang Jiang,
- Abstract summary: diffusion probabilistic models (DPMs) are being employed as mainstream models for generative artificial intelligence (AI)
We aim to establish a theoretical understanding of memorization in DPMs with 1) a memorization metric for theoretical analysis, 2) an analysis of conditional memorization with informative and random labels, and 3) two better evaluation metrics for measuring memorization.
Based on the theoretical analysis, we propose a novel data extraction method called textbfSurrogate condItional Data Extraction (SIDE) that leverages a trained on generated data as a surrogate condition to extract training data directly from unconditional diffusion models.
- Score: 76.85077961718875
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: As diffusion probabilistic models (DPMs) are being employed as mainstream models for generative artificial intelligence (AI), the study of their memorization of the raw training data has attracted growing attention. Existing works in this direction aim to establish an understanding of whether or to what extent DPMs learn by memorization. Such an understanding is crucial for identifying potential risks of data leakage and copyright infringement in diffusion models and, more importantly, for more controllable generation and trustworthy application of Artificial Intelligence Generated Content (AIGC). While previous works have made important observations of when DPMs are prone to memorization, these findings are mostly empirical, and the developed data extraction methods only work for conditional diffusion models. In this work, we aim to establish a theoretical understanding of memorization in DPMs with 1) a memorization metric for theoretical analysis, 2) an analysis of conditional memorization with informative and random labels, and 3) two better evaluation metrics for measuring memorization. Based on the theoretical analysis, we further propose a novel data extraction method called \textbf{Surrogate condItional Data Extraction (SIDE)} that leverages a classifier trained on generated data as a surrogate condition to extract training data directly from unconditional diffusion models. Our empirical results demonstrate that SIDE can extract training data from diffusion models where previous methods fail, and it is on average over 50\% more effective across different scales of the CelebA dataset.
Related papers
- Probing Language Models for Pre-training Data Detection [11.37731401086372]
We propose to utilize the probing technique for pre-training data detection by examining the model's internal activations.
Our method is simple and effective and leads to more trustworthy pre-training data detection.
arXiv Detail & Related papers (2024-06-03T13:58:04Z) - Self-Consistency Training for Density-Functional-Theory Hamiltonian Prediction [74.84850523400873]
We show that Hamiltonian prediction possesses a self-consistency principle, based on which we propose self-consistency training.
It enables the model to be trained on a large amount of unlabeled data, hence addresses the data scarcity challenge.
It is more efficient than running DFT to generate labels for supervised training, since it amortizes DFT calculation over a set of queries.
arXiv Detail & Related papers (2024-03-14T16:52:57Z) - On Memorization in Diffusion Models [46.656797890144105]
We show that memorization behaviors tend to occur on smaller-sized datasets.
We quantify the impact of the influential factors on these memorization behaviors in terms of effective model memorization (EMM)
Our study holds practical significance for diffusion model users and offers clues to theoretical research in deep generative models.
arXiv Detail & Related papers (2023-10-04T09:04:20Z) - DiffusionEngine: Diffusion Model is Scalable Data Engine for Object
Detection [41.436817746749384]
Diffusion Model is a scalable data engine for object detection.
DiffusionEngine (DE) provides high-quality detection-oriented training pairs in a single stage.
arXiv Detail & Related papers (2023-09-07T17:55:01Z) - MissDiff: Training Diffusion Models on Tabular Data with Missing Values [29.894691645801597]
This work presents a unified and principled diffusion-based framework for learning from data with missing values.
We first observe that the widely adopted "impute-then-generate" pipeline may lead to a biased learning objective.
We prove the proposed method is consistent in learning the score of data distributions, and the proposed training objective serves as an upper bound for the negative likelihood in certain cases.
arXiv Detail & Related papers (2023-07-02T03:49:47Z) - Data Contamination: From Memorization to Exploitation [5.997909991352044]
It is not clear to what extent models exploit contaminated data for downstream tasks.
We pretrain BERT models on joint corpora of Wikipedia and labeled downstream datasets, and fine-tune them on the relevant task.
Experiments with two models and three downstream tasks show that exploitation exists in some cases, but in others the models memorize the contaminated data, but do not exploit it.
arXiv Detail & Related papers (2022-03-15T20:37:16Z) - Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions.
In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data.
We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
arXiv Detail & Related papers (2022-01-11T23:01:12Z) - Graph Embedding with Data Uncertainty [113.39838145450007]
spectral-based subspace learning is a common data preprocessing step in many machine learning pipelines.
Most subspace learning methods do not take into consideration possible measurement inaccuracies or artifacts that can lead to data with high uncertainty.
arXiv Detail & Related papers (2020-09-01T15:08:23Z) - Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training.
We experimentally verify that the new dataset can significantly improve the ability of the learned FER model.
To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
arXiv Detail & Related papers (2020-05-18T09:36:51Z)
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.