{"title":"基于上下文的广告拦截使用暹罗神经网络","authors":"Shawn Collins, Emily Wu, R. Ning","doi":"10.1109/CSP55486.2022.00019","DOIUrl":null,"url":null,"abstract":"This paper proposes a new content-based ad-blocker to minimize the amount of human effort required to effectively combat pushed advertisements. Current ad-blocker models are expensive to maintain and not always effective in identifying confusable images that may play different roles across diverse websites. We investigated the possibility of solving these problems with the introduction of a deep learning, content-based ad-blocker model. More specifically, the proposed ad-blocker identifies advertisement images by combining the contained information of a given image and the content of the website it originated from. The proposed solution was prototyped and applied to a diverse selection of popular websites, achieving a detection accuracy of 98%.","PeriodicalId":187713,"journal":{"name":"2022 6th International Conference on Cryptography, Security and Privacy (CSP)","volume":"166 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Context-based Adblocker using Siamese Neural Network\",\"authors\":\"Shawn Collins, Emily Wu, R. Ning\",\"doi\":\"10.1109/CSP55486.2022.00019\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper proposes a new content-based ad-blocker to minimize the amount of human effort required to effectively combat pushed advertisements. Current ad-blocker models are expensive to maintain and not always effective in identifying confusable images that may play different roles across diverse websites. We investigated the possibility of solving these problems with the introduction of a deep learning, content-based ad-blocker model. More specifically, the proposed ad-blocker identifies advertisement images by combining the contained information of a given image and the content of the website it originated from. The proposed solution was prototyped and applied to a diverse selection of popular websites, achieving a detection accuracy of 98%.\",\"PeriodicalId\":187713,\"journal\":{\"name\":\"2022 6th International Conference on Cryptography, Security and Privacy (CSP)\",\"volume\":\"166 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 6th International Conference on Cryptography, Security and Privacy (CSP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CSP55486.2022.00019\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 6th International Conference on Cryptography, Security and Privacy (CSP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CSP55486.2022.00019","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Context-based Adblocker using Siamese Neural Network
This paper proposes a new content-based ad-blocker to minimize the amount of human effort required to effectively combat pushed advertisements. Current ad-blocker models are expensive to maintain and not always effective in identifying confusable images that may play different roles across diverse websites. We investigated the possibility of solving these problems with the introduction of a deep learning, content-based ad-blocker model. More specifically, the proposed ad-blocker identifies advertisement images by combining the contained information of a given image and the content of the website it originated from. The proposed solution was prototyped and applied to a diverse selection of popular websites, achieving a detection accuracy of 98%.