Caiqin Dong, Jian Weng, Jia-Nan Liu, Yue Zhang, Yao Tong, Anjia Yang, Yudan Cheng, Shun Hu
{"title":"Fusion: Efficient and Secure Inference Resilient to Malicious Servers","authors":"Caiqin Dong, Jian Weng, Jia-Nan Liu, Yue Zhang, Yao Tong, Anjia Yang, Yudan Cheng, Shun Hu","doi":"10.14722/ndss.2023.23199","DOIUrl":null,"url":null,"abstract":"In secure machine learning inference, most of the schemes assume that the server is semi-honest (honestly following the protocol but attempting to infer additional information). However, the server may be malicious (e.g., using a low-quality model or deviating from the protocol) in the real world. Although a few studies have considered a malicious server that deviates from the protocol, they ignore the verification of model accuracy (where the malicious server uses a low-quality model) meanwhile preserving the privacy of both the server's model and the client's inputs. To address these issues, we propose \\textit{Fusion}, where the client mixes the public samples (which have known query results) with their own samples to be queried as the inputs of multi-party computation to jointly perform the secure inference. Since a server that uses a low-quality model or deviates from the protocol can only produce results that can be easily identified by the client, \\textit{Fusion} forces the server to behave honestly, thereby addressing all those aforementioned issues without leveraging expensive cryptographic techniques. Our evaluation indicates that \\textit{Fusion} is 48.06$\\times$ faster and uses 30.90$\\times$ less communication than the existing maliciously secure inference protocol (which currently does not support the verification of the model accuracy). In addition, to show the scalability, we conduct ImageNet-scale inference on the practical ResNet50 model and it costs 8.678 minutes and 10.117 GiB of communication in a WAN setting, which is 1.18$\\times$ faster and has 2.64$\\times$ less communication than those of the semi-honest protocol.","PeriodicalId":199733,"journal":{"name":"Proceedings 2023 Network and Distributed System Security Symposium","volume":"56 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings 2023 Network and Distributed System Security Symposium","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.14722/ndss.2023.23199","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
In secure machine learning inference, most of the schemes assume that the server is semi-honest (honestly following the protocol but attempting to infer additional information). However, the server may be malicious (e.g., using a low-quality model or deviating from the protocol) in the real world. Although a few studies have considered a malicious server that deviates from the protocol, they ignore the verification of model accuracy (where the malicious server uses a low-quality model) meanwhile preserving the privacy of both the server's model and the client's inputs. To address these issues, we propose \textit{Fusion}, where the client mixes the public samples (which have known query results) with their own samples to be queried as the inputs of multi-party computation to jointly perform the secure inference. Since a server that uses a low-quality model or deviates from the protocol can only produce results that can be easily identified by the client, \textit{Fusion} forces the server to behave honestly, thereby addressing all those aforementioned issues without leveraging expensive cryptographic techniques. Our evaluation indicates that \textit{Fusion} is 48.06$\times$ faster and uses 30.90$\times$ less communication than the existing maliciously secure inference protocol (which currently does not support the verification of the model accuracy). In addition, to show the scalability, we conduct ImageNet-scale inference on the practical ResNet50 model and it costs 8.678 minutes and 10.117 GiB of communication in a WAN setting, which is 1.18$\times$ faster and has 2.64$\times$ less communication than those of the semi-honest protocol.