TY -的A2 -古普塔,Suneet Kumar AU -鲱鱼,之内沙非盟- Rizvee。Mashfiq盟——Roza Nishat斯盟——质量屋,s m . Ahsanul AU - Monirujjaman汗默罕默德盟-辛格Arjun盟——Zaguia Atef盟——Bourouis萨米PY - 2021 DA - 2021/12/16 TI - Deepfake形象的比较分析检测方法使用卷积神经网络SP - 3111676六世- 2021 AB - Z一代是一个数据驱动的一代。每个人都有人性的完整的知识在他们的手中。技术的可能性是无限的。然而,我们使用和滥用这个祝福面对使用deepfake交换。Deepfake是人工智能技术的一个新兴的子域名,一个人的脸是覆盖在另一个人的脸,这是非常著名的在社交媒体。deepfakes机器学习是主要的元素,这使得deepfake生成图像和视频相当速度更快、成本更低。尽管负面内涵与“deepfakes”,这项技术被更广泛地使用商业和个人。虽然是相对较新的,最近的技术进步使其越来越具有挑战性的检测deepfakes合成图像真实的。越来越不安的感觉已经开发了deepfake技术的出现。我们的主要目的是检测deepfake图像真实准确的。 In this research, we implemented several methods to detect deepfake images and make a comparative analysis. Our model was trained by datasets from Kaggle, which had 70,000 images from the Flickr dataset and 70,000 images produced by styleGAN. For this comparative study of the use of convolutional neural networks (CNN) to identify genuine and deepfake pictures, we trained eight different CNN models. Three of these models were trained using the DenseNet architecture (DenseNet121, DenseNet169, and DenseNet201); two were trained using the VGGNet architecture (VGG16, VGG19); one was with the ResNet50 architecture, one with the VGGFace, and one with a bespoke CNN architecture. We have also implemented a custom model that incorporates methods like dropout and padding that aid in determining whether or not the other models reflect their objectives. The results were categorized by five evaluation metrics: accuracy, precision, recall, F1-score,中华民国(接受者操作特征)曲线下的面积。在所有的模型、VGGFace表现最好的准确率达到了99%。ResNet50此外,我们获得97%,96%从DenseNet201 DenseNet169 95%, 94%从VGG19 VGG16 92%, 97%来自DenseNet121模型,90%来自自定义模型。SN - 1687 - 5265 UR - https://doi.org/10.1155/2021/3111676 - 10.1155 / 2021/3111676摩根富林明计算智力和神经科学PB - Hindawi KW - ER