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 2401.07358cs.CV
收藏

利用机器学习辨别AI生成的合成图像

Harnessing Machine Learning for Discerning AI-Generated Synthetic Images

Cornell University(康奈尔大学)

Yuyang Wang, Yizhi Hao, Amando Xu Cong

AI总结:

本研究利用CIFAKE数据集,通过迁移学习优化ResNet、VGGNet和DenseNet等深度学习模型,并与SVM和CNN基线比较,DenseNet达到97.74%准确率,显著优于传统方法,为数字媒体完整性提供有力保障。

摘要:

在数字媒体领域,AI生成的合成图像的出现给区分真实与伪造的视觉内容带来了重大挑战。这些图像通常与真实图像难以区分,对数字媒体的可信度构成威胁,并可能引发虚假信息和欺诈问题。我们的研究通过采用机器学习技术来辨别AI生成图像与真实图像,以应对这一挑战。我们方法的核心是CIFAKE数据集,这是一个包含标记为“Real”和“Fake”图像的全面集合。我们改进并适配了ResNet、VGGNet和DenseNet等先进深度学习架构,利用迁移学习提高其识别合成图像的精度。我们还将这些模型与由普通支持向量机(SVM)和自定义卷积神经网络(CNN)组成的基线模型进行比较。实验结果显著,表明我们优化的深度学习模型优于传统方法,其中DenseNet达到了97.74%的准确率。我们的应用研究通过应用和优化这些先进模型进行合成图像检测,使用多种指标进行比较分析,并展示了它们在识别AI生成图像方面优于传统机器学习技术的能力。这项研究不仅推进了数字媒体完整性领域的发展,也为未来探索数字媒体中AI生成内容的伦理和技术维度奠定了基础。

英文摘要:

In the realm of digital media, the advent of AI-generated synthetic images has introduced significant challenges in distinguishing between real and fabricated visual content. These images, often indistinguishable from authentic ones, pose a threat to the credibility of digital media, with potential implications for disinformation and fraud. Our research addresses this challenge by employing machine learning techniques to discern between AI-generated and genuine images. Central to our approach is the CIFAKE dataset, a comprehensive collection of images labeled as "Real" and "Fake". We refine and adapt advanced deep learning architectures like ResNet, VGGNet, and DenseNet, utilizing transfer learning to enhance their precision in identifying synthetic images. We also compare these with a baseline model comprising a vanilla Support Vector Machine (SVM) and a custom Convolutional Neural Network (CNN). The experimental results were significant, demonstrating that our optimized deep learning models outperform traditional methods, with DenseNet achieving an accuracy of 97.74%. Our application study contributes by applying and optimizing these advanced models for synthetic image detection, conducting a comparative analysis using various metrics, and demonstrating their superior capability in identifying AI-generated images over traditional machine learning techniques. This research not only advances the field of digital media integrity but also sets a foundation for future explorations into the ethical and technical dimensions of AI-generated content in digital media.

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。

↑