{"title":"利用深度学习检测伪造图像","authors":"Pranav Sharma, Pooja Santwani, Rachit Narula","doi":"10.35940/ijeat.a3792.1012122","DOIUrl":null,"url":null,"abstract":"This availability and requirement of data calls for the credibility and authenticity of the data. One such domain is images where tampering creates concern , leading to wide spread of misinformation and fake news. Images are transferred to initiate propagandas on social handles and other platforms. Most of these images are tampered from the authentic original content to allude people and miscommunicate malicious information. In this application, our main work is to modify the existing MobileNetV2 family of neural networks to a more relevant version, so that we can identify and differentiate tampered images from authentic images. We will further create our own convolutional neural network, to create an application which can help us to identify and differentiate tampered images from authentic images and compare our model with MobileNetV2.","PeriodicalId":13981,"journal":{"name":"International Journal of Engineering and Advanced Technology","volume":"38 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2022-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Detecting Forged Images using Deep Learning\",\"authors\":\"Pranav Sharma, Pooja Santwani, Rachit Narula\",\"doi\":\"10.35940/ijeat.a3792.1012122\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This availability and requirement of data calls for the credibility and authenticity of the data. One such domain is images where tampering creates concern , leading to wide spread of misinformation and fake news. Images are transferred to initiate propagandas on social handles and other platforms. Most of these images are tampered from the authentic original content to allude people and miscommunicate malicious information. In this application, our main work is to modify the existing MobileNetV2 family of neural networks to a more relevant version, so that we can identify and differentiate tampered images from authentic images. We will further create our own convolutional neural network, to create an application which can help us to identify and differentiate tampered images from authentic images and compare our model with MobileNetV2.\",\"PeriodicalId\":13981,\"journal\":{\"name\":\"International Journal of Engineering and Advanced Technology\",\"volume\":\"38 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-10-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Engineering and Advanced Technology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.35940/ijeat.a3792.1012122\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Engineering and Advanced Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.35940/ijeat.a3792.1012122","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
This availability and requirement of data calls for the credibility and authenticity of the data. One such domain is images where tampering creates concern , leading to wide spread of misinformation and fake news. Images are transferred to initiate propagandas on social handles and other platforms. Most of these images are tampered from the authentic original content to allude people and miscommunicate malicious information. In this application, our main work is to modify the existing MobileNetV2 family of neural networks to a more relevant version, so that we can identify and differentiate tampered images from authentic images. We will further create our own convolutional neural network, to create an application which can help us to identify and differentiate tampered images from authentic images and compare our model with MobileNetV2.