Investigating Memorization in Video Diffusion Models

2024-10-29

arXiv.org

AI Summary

Video diffusion models (VDMs) pose a risk of memorizing and regenerating training data—potentially leaking copyrighted content—yet this issue remains systematically unexplored in the video domain. This work formally defines *content memory* and *motion memory* as two orthogonal dimensions of memorization and introduces the first dedicated memory evaluation framework for VDMs. Our framework comprises: (i) decoupled quantitative metrics, (ii) a curated set of high-risk prompt templates, and (iii) a cross-modal (image + video) similarity assessment method operating at both frame-level and optical-flow-level, augmented by statistical significance testing and multi-model benchmarking. Experiments on leading open-source VDMs reveal pervasive cross-modal memorization behavior, including successful reconstruction of original training clips. We further propose a lightweight detection strategy enabling efficient identification of both content and motion memory. This work establishes foundational theory and practical tools for the safety evaluation of VDMs.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Diffusion models, widely used for image and video generation, face a significant limitation: the risk of memorizing and reproducing training data during inference, potentially generating unauthorized copyrighted content. While prior research has focused on image diffusion models (IDMs), video diffusion models (VDMs) remain underexplored. To address this gap, we first formally define the two types of memorization in VDMs (content memorization and motion memorization) in a practical way that focuses on privacy preservation and applies to all generation types. We then introduce new metrics specifically designed to separately assess content and motion memorization in VDMs. Additionally, we curate a dataset of text prompts that are most prone to triggering memorization when used as conditioning in VDMs. By leveraging these prompts, we generate diverse videos from various open-source VDMs, successfully extracting numerous training videos from each tested model. Through the application of our proposed metrics, we systematically analyze memorization across various pretrained VDMs, including text-conditional and unconditional models, on a variety of datasets. Our comprehensive study reveals that memorization is widespread across all tested VDMs, indicating that VDMs can also memorize image training data in addition to video datasets. Finally, we propose efficient and effective detection strategies for both content and motion memorization, offering a foundational approach for improving privacy in VDMs.

Problem

• Defining content and motion memorization in video diffusion models
• Developing metrics to assess memorization in video diffusion models
• Detecting and mitigating memorization to enhance privacy in VDMs

Innovation

• Defines content and motion memorization in VDMs
• Introduces metrics to assess memorization in VDMs
• Proposes detection strategies for memorization in VDMs