A Smart Privacy-Preserving Learning Method by Fake Gradients to Protect Users Items in Recommender Systems
In this paper, we study the problem of protecting privacy in recommender systems. We focus on protecting the items rated by users and propose a novel privacy-preserving matrix factorization algorithm. In our algorithm, the user will submit a fake gradient to make the central server not able to disti...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2020/6683834 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832560181339226112 |
|---|---|
| author | Guixun Luo Zhiyuan Zhang Zhenjiang Zhang Yun Liu Lifu Wang |
| author_facet | Guixun Luo Zhiyuan Zhang Zhenjiang Zhang Yun Liu Lifu Wang |
| author_sort | Guixun Luo |
| collection | DOAJ |
| description | In this paper, we study the problem of protecting privacy in recommender systems. We focus on protecting the items rated by users and propose a novel privacy-preserving matrix factorization algorithm. In our algorithm, the user will submit a fake gradient to make the central server not able to distinguish which items are selected by the user. We make the Kullback–Leibler distance between the real and fake gradient distributions to be small thus hard to be distinguished. Using theories and experiments, we show that our algorithm can be reduced to a time-delay SGD, which can be proved to have a good convergence so that the accuracy will not decline. Our algorithm achieves a good tradeoff between the privacy and accuracy. |
| format | Article |
| id | doaj-art-54e19e08104d4c4fa066636343013325 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-54e19e08104d4c4fa0666363430133252025-02-03T01:28:09ZengWileyComplexity1076-27871099-05262020-01-01202010.1155/2020/66838346683834A Smart Privacy-Preserving Learning Method by Fake Gradients to Protect Users Items in Recommender SystemsGuixun Luo0Zhiyuan Zhang1Zhenjiang Zhang2Yun Liu3Lifu Wang4School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Electronic and Information Engineering, Key Laboratory of Communication and Information Systems, Beijing Municipal Commission of Education, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Software Engineering, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Electronic and Information Engineering, Key Laboratory of Communication and Information Systems, Beijing Municipal Commission of Education, Beijing Jiaotong University, Beijing 100044, ChinaSchool of Electronic and Information Engineering, Key Laboratory of Communication and Information Systems, Beijing Municipal Commission of Education, Beijing Jiaotong University, Beijing 100044, ChinaIn this paper, we study the problem of protecting privacy in recommender systems. We focus on protecting the items rated by users and propose a novel privacy-preserving matrix factorization algorithm. In our algorithm, the user will submit a fake gradient to make the central server not able to distinguish which items are selected by the user. We make the Kullback–Leibler distance between the real and fake gradient distributions to be small thus hard to be distinguished. Using theories and experiments, we show that our algorithm can be reduced to a time-delay SGD, which can be proved to have a good convergence so that the accuracy will not decline. Our algorithm achieves a good tradeoff between the privacy and accuracy.http://dx.doi.org/10.1155/2020/6683834 |
| spellingShingle | Guixun Luo Zhiyuan Zhang Zhenjiang Zhang Yun Liu Lifu Wang A Smart Privacy-Preserving Learning Method by Fake Gradients to Protect Users Items in Recommender Systems Complexity |
| title | A Smart Privacy-Preserving Learning Method by Fake Gradients to Protect Users Items in Recommender Systems |
| title_full | A Smart Privacy-Preserving Learning Method by Fake Gradients to Protect Users Items in Recommender Systems |
| title_fullStr | A Smart Privacy-Preserving Learning Method by Fake Gradients to Protect Users Items in Recommender Systems |
| title_full_unstemmed | A Smart Privacy-Preserving Learning Method by Fake Gradients to Protect Users Items in Recommender Systems |
| title_short | A Smart Privacy-Preserving Learning Method by Fake Gradients to Protect Users Items in Recommender Systems |
| title_sort | smart privacy preserving learning method by fake gradients to protect users items in recommender systems |
| url | http://dx.doi.org/10.1155/2020/6683834 |
| work_keys_str_mv | AT guixunluo asmartprivacypreservinglearningmethodbyfakegradientstoprotectusersitemsinrecommendersystems AT zhiyuanzhang asmartprivacypreservinglearningmethodbyfakegradientstoprotectusersitemsinrecommendersystems AT zhenjiangzhang asmartprivacypreservinglearningmethodbyfakegradientstoprotectusersitemsinrecommendersystems AT yunliu asmartprivacypreservinglearningmethodbyfakegradientstoprotectusersitemsinrecommendersystems AT lifuwang asmartprivacypreservinglearningmethodbyfakegradientstoprotectusersitemsinrecommendersystems AT guixunluo smartprivacypreservinglearningmethodbyfakegradientstoprotectusersitemsinrecommendersystems AT zhiyuanzhang smartprivacypreservinglearningmethodbyfakegradientstoprotectusersitemsinrecommendersystems AT zhenjiangzhang smartprivacypreservinglearningmethodbyfakegradientstoprotectusersitemsinrecommendersystems AT yunliu smartprivacypreservinglearningmethodbyfakegradientstoprotectusersitemsinrecommendersystems AT lifuwang smartprivacypreservinglearningmethodbyfakegradientstoprotectusersitemsinrecommendersystems |