Secure tumor classification by shallow neural network using homomorphic encryption
Abstract Background Disclosure of patients’ genetic information in the process of applying machine learning techniques for tumor classification hinders the privacy of personal information. Homomorphic Encryption (HE), which supports operations between encrypted data, can be used as one of the tools...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-04-01
|
| Series: | BMC Genomics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12864-022-08469-w |
| _version_ | 1819210150644285440 |
|---|---|
| author | Seungwan Hong Jai Hyun Park Wonhee Cho Hyeongmin Choe Jung Hee Cheon |
| author_facet | Seungwan Hong Jai Hyun Park Wonhee Cho Hyeongmin Choe Jung Hee Cheon |
| author_sort | Seungwan Hong |
| collection | DOAJ |
| description | Abstract Background Disclosure of patients’ genetic information in the process of applying machine learning techniques for tumor classification hinders the privacy of personal information. Homomorphic Encryption (HE), which supports operations between encrypted data, can be used as one of the tools to perform such computation without information leakage, but it brings great challenges for directly applying general machine learning algorithms due to the limitations of operations supported by HE. In particular, non-polynomial activation functions, including softmax functions, are difficult to implement with HE and require a suitable approximation method to minimize the loss of accuracy. In the secure genome analysis competition called iDASH 2020, it is presented as a competition task that a multi-label tumor classification method that predicts the class of samples based on genetic information using HE. Methods We develop a secure multi-label tumor classification method using HE to ensure privacy during all the computations of the model inference process. Our solution is based on a 1-layer neural network with the softmax activation function model and uses the approximate HE scheme. We present an approximation method that enables softmax activation in the model using HE and a technique for efficiently encoding data to reduce computational costs. In addition, we propose a HE-friendly data filtering method to reduce the size of large-scale genetic data. Results We aim to analyze the dataset from The Cancer Genome Atlas (TCGA) dataset, which consists of 3,622 samples from 11 types of cancers, genetic features from 25,128 genes. Our preprocessing method reduces the number of genes to 4,096 or less and achieves a microAUC value of 0.9882 (85% accuracy) with a 1-layer shallow neural network. Using our model, we successfully compute the tumor classification inference steps on the encrypted test data in 3.75 minutes. As a result of exceptionally high microAUC values, our solution was awarded co-first place in iDASH 2020 Track 1: “Secure multi-label Tumor classification using Homomorphic Encryption”. Conclusions Our solution is the first result of implementing a neural network model with softmax activation using HE. Also, HE optimization methods presented in this work enable machine learning implementation using HE or other challenging HE applications. |
| first_indexed | 2024-12-23T06:06:36Z |
| format | Article |
| id | doaj.art-c86c4799970f403aa2aba50d41e42fef |
| institution | Directory Open Access Journal |
| issn | 1471-2164 |
| language | English |
| last_indexed | 2024-12-23T06:06:36Z |
| publishDate | 2022-04-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Genomics |
| spelling | doaj.art-c86c4799970f403aa2aba50d41e42fef2022-12-21T17:57:33ZengBMCBMC Genomics1471-21642022-04-0123111910.1186/s12864-022-08469-wSecure tumor classification by shallow neural network using homomorphic encryptionSeungwan Hong0Jai Hyun Park1Wonhee Cho2Hyeongmin Choe3Jung Hee Cheon4Department of Mathematical Sciences, Seoul National UniversityDepartment of Mathematical Sciences, Seoul National UniversityDepartment of Mathematical Sciences, Seoul National UniversityDepartment of Mathematical Sciences, Seoul National UniversityDepartment of Mathematical Sciences, Seoul National UniversityAbstract Background Disclosure of patients’ genetic information in the process of applying machine learning techniques for tumor classification hinders the privacy of personal information. Homomorphic Encryption (HE), which supports operations between encrypted data, can be used as one of the tools to perform such computation without information leakage, but it brings great challenges for directly applying general machine learning algorithms due to the limitations of operations supported by HE. In particular, non-polynomial activation functions, including softmax functions, are difficult to implement with HE and require a suitable approximation method to minimize the loss of accuracy. In the secure genome analysis competition called iDASH 2020, it is presented as a competition task that a multi-label tumor classification method that predicts the class of samples based on genetic information using HE. Methods We develop a secure multi-label tumor classification method using HE to ensure privacy during all the computations of the model inference process. Our solution is based on a 1-layer neural network with the softmax activation function model and uses the approximate HE scheme. We present an approximation method that enables softmax activation in the model using HE and a technique for efficiently encoding data to reduce computational costs. In addition, we propose a HE-friendly data filtering method to reduce the size of large-scale genetic data. Results We aim to analyze the dataset from The Cancer Genome Atlas (TCGA) dataset, which consists of 3,622 samples from 11 types of cancers, genetic features from 25,128 genes. Our preprocessing method reduces the number of genes to 4,096 or less and achieves a microAUC value of 0.9882 (85% accuracy) with a 1-layer shallow neural network. Using our model, we successfully compute the tumor classification inference steps on the encrypted test data in 3.75 minutes. As a result of exceptionally high microAUC values, our solution was awarded co-first place in iDASH 2020 Track 1: “Secure multi-label Tumor classification using Homomorphic Encryption”. Conclusions Our solution is the first result of implementing a neural network model with softmax activation using HE. Also, HE optimization methods presented in this work enable machine learning implementation using HE or other challenging HE applications.https://doi.org/10.1186/s12864-022-08469-wHomomorphic encryptionMulti-label classificationPrivacyNeural networkSoftmax activation |
| spellingShingle | Seungwan Hong Jai Hyun Park Wonhee Cho Hyeongmin Choe Jung Hee Cheon Secure tumor classification by shallow neural network using homomorphic encryption BMC Genomics Homomorphic encryption Multi-label classification Privacy Neural network Softmax activation |
| title | Secure tumor classification by shallow neural network using homomorphic encryption |
| title_full | Secure tumor classification by shallow neural network using homomorphic encryption |
| title_fullStr | Secure tumor classification by shallow neural network using homomorphic encryption |
| title_full_unstemmed | Secure tumor classification by shallow neural network using homomorphic encryption |
| title_short | Secure tumor classification by shallow neural network using homomorphic encryption |
| title_sort | secure tumor classification by shallow neural network using homomorphic encryption |
| topic | Homomorphic encryption Multi-label classification Privacy Neural network Softmax activation |
| url | https://doi.org/10.1186/s12864-022-08469-w |
| work_keys_str_mv | AT seungwanhong securetumorclassificationbyshallowneuralnetworkusinghomomorphicencryption AT jaihyunpark securetumorclassificationbyshallowneuralnetworkusinghomomorphicencryption AT wonheecho securetumorclassificationbyshallowneuralnetworkusinghomomorphicencryption AT hyeongminchoe securetumorclassificationbyshallowneuralnetworkusinghomomorphicencryption AT jungheecheon securetumorclassificationbyshallowneuralnetworkusinghomomorphicencryption |