Privacy-Preserving Decision-Tree Evaluation with Low Complexity for Communication
Due to the rapid development of machine-learning technology, companies can build complex models to provide prediction or classification services for customers without resources. A large number of related solutions exist to protect the privacy of models and user data. However, these efforts require c...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/5/2624 |
| _version_ | 1827752141334249472 |
|---|---|
| author | Yidi Hao Baodong Qin Yitian Sun |
| author_facet | Yidi Hao Baodong Qin Yitian Sun |
| author_sort | Yidi Hao |
| collection | DOAJ |
| description | Due to the rapid development of machine-learning technology, companies can build complex models to provide prediction or classification services for customers without resources. A large number of related solutions exist to protect the privacy of models and user data. However, these efforts require costly communication and are not resistant to quantum attacks. To solve this problem, we designed a new secure integer-comparison protocol based on fully homomorphic encryption and proposed a client-server classification protocol for decision-tree evaluation based on the secure integer-comparison protocol. Compared to existing work, our classification protocol has a relatively low communication cost and requires only one round of communication with the user to complete the classification task. Moreover, the protocol was built on a fully homomorphic-scheme-based lattice that is resistant to quantum attacks, as opposed to conventional schemes. Finally, we conducted an experimental analysis comparing our protocol with the traditional approach on three datasets. The experimental results showed that the communication cost of our scheme was <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>20</mn><mo>%</mo></mrow></semantics></math></inline-formula> of the cost of the traditional scheme. |
| first_indexed | 2024-03-11T07:10:35Z |
| format | Article |
| id | doaj.art-8b903f38135b4c32b95d1a9069a92b45 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T07:10:35Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8b903f38135b4c32b95d1a9069a92b452023-11-17T08:37:21ZengMDPI AGSensors1424-82202023-02-01235262410.3390/s23052624Privacy-Preserving Decision-Tree Evaluation with Low Complexity for CommunicationYidi Hao0Baodong Qin1Yitian Sun2School of Cyberspace Security, Xi’an University of Posts and Telecommunications, Xi’an 710121, ChinaSchool of Cyberspace Security, Xi’an University of Posts and Telecommunications, Xi’an 710121, ChinaSchool of Cyberspace Security, Xi’an University of Posts and Telecommunications, Xi’an 710121, ChinaDue to the rapid development of machine-learning technology, companies can build complex models to provide prediction or classification services for customers without resources. A large number of related solutions exist to protect the privacy of models and user data. However, these efforts require costly communication and are not resistant to quantum attacks. To solve this problem, we designed a new secure integer-comparison protocol based on fully homomorphic encryption and proposed a client-server classification protocol for decision-tree evaluation based on the secure integer-comparison protocol. Compared to existing work, our classification protocol has a relatively low communication cost and requires only one round of communication with the user to complete the classification task. Moreover, the protocol was built on a fully homomorphic-scheme-based lattice that is resistant to quantum attacks, as opposed to conventional schemes. Finally, we conducted an experimental analysis comparing our protocol with the traditional approach on three datasets. The experimental results showed that the communication cost of our scheme was <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>20</mn><mo>%</mo></mrow></semantics></math></inline-formula> of the cost of the traditional scheme.https://www.mdpi.com/1424-8220/23/5/2624secure integer comparisonfully homomorphic encryptiondecisional tree |
| spellingShingle | Yidi Hao Baodong Qin Yitian Sun Privacy-Preserving Decision-Tree Evaluation with Low Complexity for Communication Sensors secure integer comparison fully homomorphic encryption decisional tree |
| title | Privacy-Preserving Decision-Tree Evaluation with Low Complexity for Communication |
| title_full | Privacy-Preserving Decision-Tree Evaluation with Low Complexity for Communication |
| title_fullStr | Privacy-Preserving Decision-Tree Evaluation with Low Complexity for Communication |
| title_full_unstemmed | Privacy-Preserving Decision-Tree Evaluation with Low Complexity for Communication |
| title_short | Privacy-Preserving Decision-Tree Evaluation with Low Complexity for Communication |
| title_sort | privacy preserving decision tree evaluation with low complexity for communication |
| topic | secure integer comparison fully homomorphic encryption decisional tree |
| url | https://www.mdpi.com/1424-8220/23/5/2624 |
| work_keys_str_mv | AT yidihao privacypreservingdecisiontreeevaluationwithlowcomplexityforcommunication AT baodongqin privacypreservingdecisiontreeevaluationwithlowcomplexityforcommunication AT yitiansun privacypreservingdecisiontreeevaluationwithlowcomplexityforcommunication |