扩散模型的图像复制检测

Image Copy Detection for Diffusion Models

September 30, 2024

作者: Wenhao Wang, Yifan Sun, Zhentao Tan, Yi Yang

cs.AI

摘要

扩散模型生成的图像在数字艺术和视觉营销中越来越受欢迎。然而，这些生成的图像可能复制现有内容，带来内容原创性的挑战。现有的图像复制检测（ICD）模型虽然在检测手工复制品方面准确，但忽视了来自扩散模型的挑战。这促使我们引入ICDiff，这是专门针对扩散模型的第一个ICD。为此，我们构建了一个扩散复制（D-Rep）数据集，并相应提出了一种新颖的深度嵌入方法。D-Rep使用一种最先进的扩散模型（稳定扩散 V1.5）生成了 40,000 个图像-复制对，这些对被手动注释为 6 个复制级别，范围从 0（无复制）到 5（完全复制）。我们的方法，PDF-嵌入，将每个图像-复制对的复制级别转换为概率密度函数（PDF）作为监督信号。直觉是相邻复制级别的概率应该是连续且平滑的。实验结果表明，PDF-嵌入在D-Rep测试集上超过了协议驱动方法和非PDF选择。此外，通过利用PDF-嵌入，我们发现知名扩散模型对开源库的复制比例范围在 10% 到 20% 之间。

English

Images produced by diffusion models are increasingly popular in digital artwork and visual marketing. However, such generated images might replicate content from existing ones and pose the challenge of content originality. Existing Image Copy Detection (ICD) models, though accurate in detecting hand-crafted replicas, overlook the challenge from diffusion models. This motivates us to introduce ICDiff, the first ICD specialized for diffusion models. To this end, we construct a Diffusion-Replication (D-Rep) dataset and correspondingly propose a novel deep embedding method. D-Rep uses a state-of-the-art diffusion model (Stable Diffusion V1.5) to generate 40, 000 image-replica pairs, which are manually annotated into 6 replication levels ranging from 0 (no replication) to 5 (total replication). Our method, PDF-Embedding, transforms the replication level of each image-replica pair into a probability density function (PDF) as the supervision signal. The intuition is that the probability of neighboring replication levels should be continuous and smooth. Experimental results show that PDF-Embedding surpasses protocol-driven methods and non-PDF choices on the D-Rep test set. Moreover, by utilizing PDF-Embedding, we find that the replication ratios of well-known diffusion models against an open-source gallery range from 10% to 20%.