{"title":"基于深度学习的音频欺骗攻击检测DFWF模型","authors":"Kottilingam Kottursamy","doi":"10.36548/jaicn.2022.3.004","DOIUrl":null,"url":null,"abstract":"One of the biggest threats in the speaker verification system is that of fake audio attacks. Over the years several detection approaches have been introduced that were designed to provide efficient and spoof-proof data-specific scenarios. However, the speaker verification system is still exposed to fake audio threats. Hence to address this issue, several authors have proposed methodologies to retrain and finetune the input data. The drawback with retraining and fine-tuning is that retraining requires high computation resources and time while fine-tuning results in degradation of performance. Moreover, in certain situations, the previous data becomes unavailable and cannot be accessed immediately. In this paper, we have proposed a solution that detects fake without continual-learning based methods and fake detection without forgetting in order to develop a new model which is capable of detecting spoofing attacks in an incremental fashion. In order to retain original model memory, knowledge distillation loss is introduced. In several scenarios, the distribution of genuine voice is said to be very consistent. In several scenarios, there is consistency in distribution of genuine voice hence a similarity loss is embedded additionally to perform a positive sample alignment. The output of the proposed work indicates an error rate reduction of up to 80% as observed and recorded.","PeriodicalId":74231,"journal":{"name":"Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep Learning based DFWF Model for Audio Spoofing Attack Detection\",\"authors\":\"Kottilingam Kottursamy\",\"doi\":\"10.36548/jaicn.2022.3.004\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"One of the biggest threats in the speaker verification system is that of fake audio attacks. Over the years several detection approaches have been introduced that were designed to provide efficient and spoof-proof data-specific scenarios. However, the speaker verification system is still exposed to fake audio threats. Hence to address this issue, several authors have proposed methodologies to retrain and finetune the input data. The drawback with retraining and fine-tuning is that retraining requires high computation resources and time while fine-tuning results in degradation of performance. Moreover, in certain situations, the previous data becomes unavailable and cannot be accessed immediately. In this paper, we have proposed a solution that detects fake without continual-learning based methods and fake detection without forgetting in order to develop a new model which is capable of detecting spoofing attacks in an incremental fashion. In order to retain original model memory, knowledge distillation loss is introduced. In several scenarios, the distribution of genuine voice is said to be very consistent. In several scenarios, there is consistency in distribution of genuine voice hence a similarity loss is embedded additionally to perform a positive sample alignment. The output of the proposed work indicates an error rate reduction of up to 80% as observed and recorded.\",\"PeriodicalId\":74231,\"journal\":{\"name\":\"Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-09-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.36548/jaicn.2022.3.004\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Multiscale multimodal medical imaging : Third International Workshop, MMMI 2022, held in conjunction with MICCAI 2022, Singapore, September 22, 2022, proceedings","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.36548/jaicn.2022.3.004","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Deep Learning based DFWF Model for Audio Spoofing Attack Detection
One of the biggest threats in the speaker verification system is that of fake audio attacks. Over the years several detection approaches have been introduced that were designed to provide efficient and spoof-proof data-specific scenarios. However, the speaker verification system is still exposed to fake audio threats. Hence to address this issue, several authors have proposed methodologies to retrain and finetune the input data. The drawback with retraining and fine-tuning is that retraining requires high computation resources and time while fine-tuning results in degradation of performance. Moreover, in certain situations, the previous data becomes unavailable and cannot be accessed immediately. In this paper, we have proposed a solution that detects fake without continual-learning based methods and fake detection without forgetting in order to develop a new model which is capable of detecting spoofing attacks in an incremental fashion. In order to retain original model memory, knowledge distillation loss is introduced. In several scenarios, the distribution of genuine voice is said to be very consistent. In several scenarios, there is consistency in distribution of genuine voice hence a similarity loss is embedded additionally to perform a positive sample alignment. The output of the proposed work indicates an error rate reduction of up to 80% as observed and recorded.