{"title":"人脸检测网络上对抗性攻击的检测方法","authors":"E. Myasnikov, Vitaly Konovalov","doi":"10.1109/ITNT57377.2023.10139021","DOIUrl":null,"url":null,"abstract":"The paper is concerned with the problem of detecting adversarial attacks against face detection networks. The paper reviews existing adversarial attacks, as well as defense techniques. A novel defense method is proposed, which provides improved detection quality compared to the base technique. Comparative experiments are conducted on a dataset composed of original and fake images obtained using FGSM and MI_FGSM techniques with various parameters.","PeriodicalId":296438,"journal":{"name":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Method for detection of adversarial attacks on face detection networks\",\"authors\":\"E. Myasnikov, Vitaly Konovalov\",\"doi\":\"10.1109/ITNT57377.2023.10139021\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The paper is concerned with the problem of detecting adversarial attacks against face detection networks. The paper reviews existing adversarial attacks, as well as defense techniques. A novel defense method is proposed, which provides improved detection quality compared to the base technique. Comparative experiments are conducted on a dataset composed of original and fake images obtained using FGSM and MI_FGSM techniques with various parameters.\",\"PeriodicalId\":296438,\"journal\":{\"name\":\"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)\",\"volume\":\"76 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-04-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ITNT57377.2023.10139021\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IX International Conference on Information Technology and Nanotechnology (ITNT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ITNT57377.2023.10139021","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Method for detection of adversarial attacks on face detection networks
The paper is concerned with the problem of detecting adversarial attacks against face detection networks. The paper reviews existing adversarial attacks, as well as defense techniques. A novel defense method is proposed, which provides improved detection quality compared to the base technique. Comparative experiments are conducted on a dataset composed of original and fake images obtained using FGSM and MI_FGSM techniques with various parameters.