数据隐私保护的社会化推荐协议

doi:10.11959/j.issn.1000-436x.2015322

通信学报 ›› 2015, Vol. 36 ›› Issue (12): 131-138.doi: 10.11959/j.issn.1000-436x.2015322

数据隐私保护的社会化推荐协议

刘曙曙^1,²,刘安^1,²,赵雷^1,²,刘冠峰^1,²,李直旭^1,²,郑凯^1,²,周晓方^1,²

¹ 苏州大学计算机科学与技术学院，江苏苏州 215000
² 江苏省软件新技术与产业化协同创新中心，江苏南京 211102

出版日期:2015-12-25 发布日期:2017-07-17
基金资助:
国家自然科学基金资助项目;国家自然科学基金资助项目;国家自然科学基金资助项目;国家自然科学基金资助项目

Preserving data privacy in social recommendation

Shu-shu LIU^1,²,An LIU^1,²,Lei ZHAO^1,²,Guan-feng LIU^1,²,Zhi-xu LI^1,²,Kai ZHENG^1,²,Xiao-fang ZHOU^1,²

¹ School of Computer Science and Technology,Soochow University,Suzhou 215000,China
² Collaborative Innovation Center of Novel Software Technology and Industrialization,Nanjing 211102,China

Online:2015-12-25 Published:2017-07-17
Supported by:
The National Natural Science Foundation of China;The National Natural Science Foundation of China;The National Natural Science Foundation of China;The National Natural Science Foundation of China

摘要/Abstract

摘要：

基于邻域的社会化推荐需要同时依赖用户的历史行为数据和完善的社交网络拓扑图，但通常这些数据分别属于不同平台，如推荐系统服务提供商和社交网络服务提供商。出于维护自身数据价值及保护用户隐私的考虑，他们并不愿意将数据信息提供给其他方。针对这一现象，提出了2种数据隐私保护的社会化推荐协议，可以在保护推荐系统服务提供商和社交网络服务提供商的数据隐私的同时，为用户提供精准的推荐服务。其中，基于不经意传输的社会化推荐，计算代价较小，适用于对推荐效率要求较高的应用；基于同态加密的社会化推荐，安全程度更高，适用于对数据隐私要求较高的应用。在4组真实数据集上的实验表明，提出的2种方案切实可行，用户可以根据自身需求选择合适的方案。

关键词: 推荐系统, 不经意传输, 同态加密, Yao’s协议

Abstract:

Social recommendation is a method which requires the participants of both user’s historical behavior data and social network,which generally belong to different parties,such as recommendation system service provider and social network service provider.Considering the fact that in order to maintain the value of their own data interests and user’s privacy,none of them will provide data information to the other,two privacy preserving protocols are proposed for efficient computation of social recommendation which needs the cooperation of two parties (recommendation system service provider and social network service provider).Both protocols enable two parties to compute the social recommendation without revealing their private data to each other.The protocol based on the well-known oblivious transfer multiplication has a low cost,and is suitable for the application of high efficiency requirements.And the one based on homomorphic cryptosystem has a better privacy preserving,and is more suitable for the application of higher data privacy requirements.Experimental results on the four real datasets show those two protocols are efficient and practical.Users are suggested to choose the appropriate protocol according to their own need.

Key words: recommendation system, oblivious transfer, homomorphic encryption, Yao’s protocol

刘曙曙,刘安,赵雷,刘冠峰,李直旭,郑凯,周晓方. 数据隐私保护的社会化推荐协议[J]. 通信学报, 2015, 36(12): 131-138.

Shu-shu LIU,An LIU,Lei ZHAO,Guan-feng LIU,Zhi-xu LI,Kai ZHENG,Xiao-fang ZHOU. Preserving data privacy in social recommendation[J]. Journal on Communications, 2015, 36(12): 131-138.

图/表 6

图1

图2

表1

表2

表3

表4

参考文献 14

[1]	KONSTAS I , STATHOPOULOS V , JOSE J M . On social networks and collaborative recommendation[A]. 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval[C]. ACM, 2009. 195-202.
[2]	YUAN Q , ZHAO S , CHEN L ,et al. Augmenting collaborative recommender by fusing explicit social relationships[A]. Workshop on Recommender Systems and the Social Web[C]. 2009.2009.
[3]	JORGENSEN Z , YU T . A privacy-preserving framework for personalized,social recommendations[A]. EDBT[C]. 2014. 571-582.
[4]	HAN S , NG W K , YU P S . Privacy-preserving singular value decomposition[A]. ICDE[C]. 2009.
[5]	CANNY J . Collaborative filtering with privacy[A]. Security and Privacy,Proceedings of 2002 IEEE Symposium[C]. IEEE, 2002. 45-57.
[6]	MILLER B N , KONSTAN J A , RIEDL J . PocketLens:toward a personal recommender system[J]. ACM Transactions on Information Systems (TOIS), 2004,22(3): 437-476.
[7]	POLAT H , DU W . Privacy-preserving collaborative filtering[J]. International Journal of Electronic Commerce, 2005,9(4): 9-35.
[8]	BERKOVSKY S , EYTANI Y , KUFLIK T ,et al. Enhancing privacy and preserving accuracy of a distributed collaborative filtering[A]. 2007 ACM Conference on Recommender Systems[C]. ACM, 2007. 9-16.
[9]	YAO A . How to generate and exchange secrets[A]. Foundations of Computer Science 27th Annual Symposium on[C]. 1986. 162-167.
[10]	LINDELL Y , PINKAS B . A proof of security of Yao’s protocol for two-party computation[J]. Journal of Cryptology, 2009,22(2): 161-188.
[11]	HUANG Y , EVANS D , KATZ J ,et al. Faster secure two-party computation using garbled circuits[A]. USENIX Security Symposium[C]. 2011,201(1).
[12]	NAOR M , PINKAS B . Efficient oblivious transfer protocols[A]. Proceedings of the Twelfth Annual ACM-SIAM Symposium on Discrete Algorithms,Society for Industrial and Applied Mathematics[C]. 2001. 448-457.
[13]	GILBOA N . Two party RSA key generation[A]. Advances in Cryptology—CRYPTO’99[C]. Springer Berlin Heidelberg, 1999. 116-129.
[14]	CORMEN T H . Introduction to Algorithms[M]. MIT Press, 2009.

步骤	基于不经意传输的推荐	基于同态加密的社会化推荐
步骤1	\|E_t\|不经意传输乘法	\|U\|加密，\|I\|指数计算
步骤2	(3t+1)\|I\|非异或门	\|I\|加密，\|I\|解密，\|I\|指数计算
步骤3	—	(3t+1)\|I\|非异或门

数据	Last.fm	Flixster	Brightkite	Gowalla
\|U\|	1 892	786 936	58 228	196 591
\|E_s\|	12 717	7 058 819	214 078	950 327
\|I\|	17 632	48 796	314 417	1 280 969
\|E_t\|	92 198	8 196 077	4 491 143	6 442 890

数据集	步骤1/min	步骤2/min	总时间/min
Last.fm	2.39	1.22	3.61
Flixster	161.54	3.39	164.93
Brightkite	10.25	23.27	33.52
Gowalla	162.52	88.55	251.07

数据集	步骤1/min	步骤2/min	步骤3/min	总时间/min
Last.fm	4.14	7.11	1.22	12.48
Flixster	102.95	19.40	3.39	125.74
Brightkite	70.37	134.23	23.27	227.87
Gowalla	249.92	467.85	88.55	806.32

[1]	马鑫迪, 李清华, 姜奇, 马卓, 高胜, 田有亮, 马建峰. 面向Non-IID数据的拜占庭鲁棒联邦学习[J]. 通信学报, 2023, 44(6): 138-153.
[2]	余晟兴, 陈钟. 基于同态加密的高效安全联邦学习聚合框架[J]. 通信学报, 2023, 44(1): 14-28.
[3]	杨亚涛, 刘德莉, 刘培鹤, 曾萍, 肖嵩. BFV-Blockchainvoting：支持BFV全同态加密的区块链电子投票系统[J]. 通信学报, 2022, 43(9): 100-111.
[4]	张学旺, 黎志鸿, 林金朝. 基于公平盲签名和分级加密的联盟链隐私保护方案[J]. 通信学报, 2022, 43(8): 131-141.
[5]	于海宁, 张宏莉, 余翔湛, 曲家兴, 葛蒙蒙. 隐私保护的轨迹相似度计算方法[J]. 通信学报, 2022, 43(11): 1-13.
[6]	马立川, 彭佳怡, 裴庆祺, 朱浩瑾. 高效的决策树隐私分类服务协议[J]. 通信学报, 2021, 42(8): 80-89.
[7]	高胜, 向康, 田有亮, 谭伟杰, 冯涛, 吴晓雪. 基于BCP的联合委托学习模型及协议[J]. 通信学报, 2021, 42(5): 137-148.
[8]	李瑞琪, 贾春福, 王雅飞. 基于NTRU的多密钥同态代理重加密方案及其应用[J]. 通信学报, 2021, 42(3): 11-22.
[9]	贾春福, 李瑞琪, 王雅飞. 基于同态加密的DBSCAN聚类隐私保护方案[J]. 通信学报, 2021, 42(2): 1-11.
[10]	周由胜,谭畅,唐飞. 面向雾增强型工业物联网的多维安全查询方案[J]. 通信学报, 2020, 41(8): 175-186.
[11]	田有亮,李秋贤,张铎,王琳杰. 可证明安全的理性委托计算协议[J]. 通信学报, 2019, 40(7): 135-143.
[12]	王斌,张磊,张国印. 基于多方安全计算的属性泛化mix-zone[J]. 通信学报, 2019, 40(4): 83-94.
[13]	蒋文贤,张振兴,吴晶晶. 基于可逆数字水印认证的无线传感网数据融合协议[J]. 通信学报, 2018, 39(3): 118-127.
[14]	汤永利,胡明星,刘琨,叶青,闫玺玺. 新的格上基于身份的全同态加密方案[J]. 通信学报, 2017, 38(5): 39-47.
[15]	郑永辉,康元基,顾纯祥,董辉. 环上基于属性的全同态加密体制设计[J]. 通信学报, 2017, 38(4): 55-63.

数据隐私保护的社会化推荐协议

Preserving data privacy in social recommendation

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 14

相关文章 15

Metrics

推荐阅读 0