Design method of secure computing protocol for deep neural network
Aiming at the information leakage problem in the process of deep neural network model calculation,a series of secure and efficient interactive computing protocols were designed between two non-collusive edge servers in combination with the additive secret sharing scheme.Since the nonlinear function...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
POSTS&TELECOM PRESS Co., LTD
2020-08-01
|
| Series: | 网络与信息安全学报 |
| Subjects: | |
| Online Access: | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2020050 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841529943055400960 |
|---|---|
| author | Renwan BI Qianxin CHEN Jinbo XIONG Ximeng LIU |
| author_facet | Renwan BI Qianxin CHEN Jinbo XIONG Ximeng LIU |
| author_sort | Renwan BI |
| collection | DOAJ |
| description | Aiming at the information leakage problem in the process of deep neural network model calculation,a series of secure and efficient interactive computing protocols were designed between two non-collusive edge servers in combination with the additive secret sharing scheme.Since the nonlinear function cannot be split directly,a set of basic conversion protocols were proposed to realize the secure conversion of additive and multiplicative shares.After a few invokes,the power,comparison,exponential,logarithm,division and other low-level functions can be calculated securely.Due to the characteristics of data transfer and computation,the proposed protocols can be extended to array computation.Theoretical analysis ensures the correctness,efficiency and security of these protocols.The experimental results show that the error of these protocols is negligible,and the computational costs and communication overhead are better than the existing schemes. |
| format | Article |
| id | doaj-art-1aa39e70518e4ee2b57e298bf999f9ab |
| institution | Kabale University |
| issn | 2096-109X |
| language | English |
| publishDate | 2020-08-01 |
| publisher | POSTS&TELECOM PRESS Co., LTD |
| record_format | Article |
| series | 网络与信息安全学报 |
| spelling | doaj-art-1aa39e70518e4ee2b57e298bf999f9ab2025-01-15T03:14:18ZengPOSTS&TELECOM PRESS Co., LTD网络与信息安全学报2096-109X2020-08-01613013959560444Design method of secure computing protocol for deep neural networkRenwan BIQianxin CHENJinbo XIONGXimeng LIUAiming at the information leakage problem in the process of deep neural network model calculation,a series of secure and efficient interactive computing protocols were designed between two non-collusive edge servers in combination with the additive secret sharing scheme.Since the nonlinear function cannot be split directly,a set of basic conversion protocols were proposed to realize the secure conversion of additive and multiplicative shares.After a few invokes,the power,comparison,exponential,logarithm,division and other low-level functions can be calculated securely.Due to the characteristics of data transfer and computation,the proposed protocols can be extended to array computation.Theoretical analysis ensures the correctness,efficiency and security of these protocols.The experimental results show that the error of these protocols is negligible,and the computational costs and communication overhead are better than the existing schemes.http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2020050deep neural networkadditive secret sharingsecure computing protocoladd-multiply transformationarray unit |
| spellingShingle | Renwan BI Qianxin CHEN Jinbo XIONG Ximeng LIU Design method of secure computing protocol for deep neural network 网络与信息安全学报 deep neural network additive secret sharing secure computing protocol add-multiply transformation array unit |
| title | Design method of secure computing protocol for deep neural network |
| title_full | Design method of secure computing protocol for deep neural network |
| title_fullStr | Design method of secure computing protocol for deep neural network |
| title_full_unstemmed | Design method of secure computing protocol for deep neural network |
| title_short | Design method of secure computing protocol for deep neural network |
| title_sort | design method of secure computing protocol for deep neural network |
| topic | deep neural network additive secret sharing secure computing protocol add-multiply transformation array unit |
| url | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2020050 |
| work_keys_str_mv | AT renwanbi designmethodofsecurecomputingprotocolfordeepneuralnetwork AT qianxinchen designmethodofsecurecomputingprotocolfordeepneuralnetwork AT jinboxiong designmethodofsecurecomputingprotocolfordeepneuralnetwork AT ximengliu designmethodofsecurecomputingprotocolfordeepneuralnetwork |