ASAP：用于识别和分析AI生成图像中图像模式的视觉分析系统
ASAP: Visual Analytics for Identifying and Analyzing Image Patterns in AI-generated Images
浏览论文内容
中文总结 AI 辅助
本文提出ASAP，一个交互式可视化系统，利用CLIP适配编码器和影响测量技术识别并量化AI生成图像中的欺骗性模式，支持多模型比较，并通过用户研究和基准测试验证其有效性。
中文摘要 AI 辅助
生成式图像模型能够产生高度逼真的图像，这引发了关于其被滥用以创建欺骗性内容的担忧。当前的深度伪造方法面临若干挑战，包括泛化能力有限、缺乏可解释性以及可操作性差。为帮助解决这些问题，我们提出了ASAP，一个交互式可视化系统，旨在使用户能够分析和总结AI生成图像中的欺骗性模式。ASAP引入了一种新颖的CLIP适配图像编码器，生成可解释的表示，从而通过计算出的掩码提取有影响力的像素区域。这种方法通过影响测量技术促进了关键欺骗性特征的识别。这些后端技术被集成到一个视觉分析仪表板中，允许用户量化和分析包含真实图像和AI生成图像集合中指示真实性的模式。该方法还支持对各种生成模型（包括GAN和扩散模型）的比较分析。我们通过用户研究和两个使用既定假图像检测基准的应用场景展示了ASAP的有效性，展示了其有效提取和量化欺骗性模式的能力。
英文摘要
Generative image models can produce highly realistic images, raising concerns about potential misuse in creating deceptive content. Current deepfake approaches face several challenges, including limited generalizability, lack of interpretability, and poor actionability. To help address these, we present ASAP, an interactive visualization system designed to empower users in the analysis and summarization of deceptive patterns in AI-generated images. ASAP introduces a novel CLIP-adapted image encoder that generates interpretable representations, enabling the extraction of influential pixel regions via calculated masks. This approach facilitates the identification of key deceptive features through influence measurement techniques. These backend techniques are integrated into a visual analytics dashboard that allows users to quantify and analyze authenticity-indicative patterns in image collections containing both authentic and AI-generated images. This approach also supports the comparative analysis of various generative models, including GANs and diffusion models. We demonstrate ASAP's efficacy through a user study and two application scenarios using established fake image detection benchmarks, showcasing its ability to effectively extract and quantify deceptive patterns.
发表机构
- Arizona State University（亚利桑那州立大学）
- University of Maryland（马里兰大学）
- Fujitsu Research of America（富士通美国研究院）
- IBM Research（IBM研究院）
机构由 AI 辅助整理，请以论文原文为准。
