arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2307.06272cs.CVcs.CRcs.LG
收藏

揭露伪造:高效检测扩散模型生成图像

Exposing the Fake: Effective Diffusion-Generated Images Detection

University of Electronic Science and Technology of China(电子科技大学);Drexel University(德雷塞尔大学)

Ruipeng Ma, Jinhao Duan, Fei Kong, Xiaoshuang Shi, Kaidi Xu

AI总结:

针对扩散生成图像检测研究不足及其安全隐私风险,提出利用确定性反向与去噪误差的SeDID方法,含统计与神经网络两版本,检测性能优于现有方法。

摘要:

随着去噪扩散概率模型(DDPM)和文本到图像扩散模型等基于扩散的生成模型出现,图像合成取得了显著进展。尽管这些模型效果显著,但专门用于检测扩散生成图像的研究仍然匮乏,而这类图像可能带来潜在的安全与隐私风险。本文通过提出一种名为“扩散生成图像检测的逐步误差”(Stepwise Error for Diffusion-generated Image Detection,SeDID)的新型检测方法来填补这一空白。SeDID包含基于统计的SeDID_Stat和基于神经网络的SeDID_NNs,利用扩散模型的独特属性,即确定性反向和确定性去噪计算误差。评估表明,在应用于扩散模型时,SeDID的性能优于现有方法。因此,本研究为区分扩散模型生成图像作出了关键贡献,标志着人工智能安全领域迈出重要一步。

英文摘要:

Image synthesis has seen significant advancements with the advent of diffusion-based generative models like Denoising Diffusion Probabilistic Models (DDPM) and text-to-image diffusion models. Despite their efficacy, there is a dearth of research dedicated to detecting diffusion-generated images, which could pose potential security and privacy risks. This paper addresses this gap by proposing a novel detection method called Stepwise Error for Diffusion-generated Image Detection (SeDID). Comprising statistical-based $\text{SeDID}_{\text{Stat}}$ and neural network-based $\text{SeDID}_{\text{NNs}}$, SeDID exploits the unique attributes of diffusion models, namely deterministic reverse and deterministic denoising computation errors. Our evaluations demonstrate SeDID's superior performance over existing methods when applied to diffusion models. Thus, our work makes a pivotal contribution to distinguishing diffusion model-generated images, marking a significant step in the domain of artificial intelligence security.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑