{"type":"ScholarlyArticle","title":"Novel Collaborative Filtering Recommender Friendly to Privacy Protection","authors":[{"name":"Jun Wang","slug":"jun-wang","given":"Jun","family":"Wang","affiliation":"Interdisciplinary Centre for Security, Reliability and Trust , University of Luxembourg"},{"name":"Qiang Tang","slug":"qiang-tang","given":"Qiang","family":"Tang","affiliation":"Luxembourg Institute of Science and Technology"},{"name":"Afonso Arriaga","slug":"afonso-arriaga","given":"Afonso","family":"Arriaga","affiliation":"INCERT GIE , Luxembourg"},{"name":"Peter Y. A. Ryan","slug":"peter-y-a-ryan","given":"Peter Y. A.","family":"Ryan","affiliation":"Interdisciplinary Centre for Security, Reliability and Trust , University of Luxembourg"}],"abstract":"Nowadays, recommender system is an indispensable tool in many information services, and a large number of algorithms have been designed and implemented. However, fed with very large datasets, state-of-the-art recommendation algorithms often face an efficiency bottleneck, i.e., it takes huge amount of computing resources to train a recommendation model. In order to satisfy the needs of privacy-savvy users who do not want to disclose their information to the service provider, the complexity of most existing solutions becomes prohibitive. As such, it is an interesting research question to design simple and efficient recommendation algorithms that achieve reasonable accuracy and facilitate privacy protection at the same time.\r\n\r\nIn this paper, we propose an efficient recommendation algorithm, named CryptoRec, which has two nice properties: (1) can estimate a new user's preferences by directly using a model pre-learned from an expert dataset, and the new user's data is not required to train the model; (2) can compute recommendations with only addition and multiplication operations. As to the evaluation, we first test the recommendation accuracy on three real-world datasets and show that CryptoRec is competitive with state-of-the-art recommenders. Then, we evaluate the performance of the privacy-preserving variants of CryptoRec and show that predictions can be computed in seconds on a PC. In contrast, existing solutions will need tens or hundreds of hours on more powerful computers.","doi":"10.24963/ijcai.2019/668","url":"https://ijcai.org/proceedings/2019/668","pdf":"https://ijcai.org/proceedings/2019/0668.pdf","markdown":"https://ijcai.org/proceedings/2019/668.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/668","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Multidisciplinary Topics and Applications","track":"Main track","number":668,"pages":{"first":4809,"last":4815},"keywords":["Multidisciplinary Topics and Applications: Security and Privacy","Machine Learning: Recommender Systems"],"videos":[],"references":[{"position":1,"raw":"[Berlioz et al., 2015] Arnaud Berlioz, Friedman Arik, Ali Kaafar Mohamed, Boreli Roksana, and Berkovsky Shlomo. Applying differential privacy to matrix factor- ization. In Proceedings of the 9th ACM Conference on Recommender Systems, pages 107-114, 2015.","title":"Applying differential privacy to matrix factorization","authors":"Berlioz","year":"2015","venue":"Proceedings of the 9th ACM Conference on Recommender Systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Canny, 2002] John Canny. Collaborative filtering with pri- vacy. In IEEE Symposium on Security and Privacy, pages 45-57. IEEE, 2002.","title":"Collaborative filtering with privacy","authors":"John Canny","year":"2002","venue":"IEEE Symposium on Security and Privacy","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cantador et al., 2015] Iván Cantador, Ignacio Fernández- Tobías, Shlomo Berkovsky, and Paolo Cremonesi. Cross- domain recommender systems. In Recommender Systems Handbook, pages 919-959. Springer, 2015.","title":"Crossdomain recommender systems","authors":"Iván Cantador, Ignacio Fernández-Tobías, Shlomo Berkovsky, Paolo Cremonesi","year":"2015","venue":"Recommender Systems Handbook","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2017] Hao Chen, Kim Laine, and Rachel Player. Simple encrypted arithmetic library-seal v2. 1. In International Conference on Financial Cryptography and Data Security, pages 3-18. Springer, 2017.","title":"Simple encrypted arithmetic library-seal v2. 1","authors":"Kim Hao Chen, Rachel Laine, Player","year":"2017","venue":"International Conference on Financial Cryptography and Data Security","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[CSIRO, 2018] CSIRO. python-paillier, 2018.","title":"CSIRO. python-paillier","authors":null,"year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Desrosiers and Karypis, 2011] Christian Desrosiers and George Karypis. A comprehensive survey of neighborhood-based recommendation methods. Recom- mender systems handbook, pages 107-144, 2011.","title":"Christian Desrosiers and George Karypis. A comprehensive survey of neighborhood-based recommendation methods","authors":"Karypis Desrosiers","year":"2011","venue":"Recommender systems handbook","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Fan and Vercauteren, 2012] Junfeng Fan and Frederik Ver- cauteren. Somewhat practical fully homomorphic encryp- tion. IACR Cryptology ePrint Archive, 2012:144, 2012.","title":"Junfeng Fan and Frederik Vercauteren. Somewhat practical fully homomorphic encryption","authors":"Fan, Vercauteren","year":"2012","venue":"IACR Cryptology ePrint Archive","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gentry, 2009] Craig Gentry. Fully homomorphic encryption using ideal lattices. In STOC, volume 9, pages 169-178, 2009.","title":"Fully homomorphic encryption using ideal lattices","authors":"Craig Gentry","year":"2009","venue":"STOC","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gilad-Bachrach et al., 2016] Ran Gilad-Bachrach, Nathan Dowlin, Kim Laine, Kristin Lauter, Michael Naehrig, and John Wernsing. Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy. In In- ternational Conference on Machine Learning, 2016.","title":"Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy","authors":"Gilad-Bachrach","year":"2016","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Grouplens, 2010] Grouplens. Grouplens Moivelens, 2010.","title":"Grouplens. Grouplens Moivelens","authors":"Grouplens","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Han et al., 2015] Song Han, Huizi Mao, and William J Dally. Deep compression: Compressing deep neural net- works with pruning, trained quantization and huffman cod- ing. arXiv preprint arXiv:1510.00149, 2015.","title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","authors":"Han","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kim et al., 2016] Sungwook Kim, Kim Jinsu, Koo Dongy- oung, Kim Yuna, Yoon Hyunsoo, and Shin Junbum. Effi- cient privacy-preserving matrix factorization via fully ho- momorphic encryption: Extended abstract. In Proceed- ings of the 11th ACM on Asia Conference on Computer and Communications Security, pages 617-628, 2016.","title":"Efficient privacy-preserving matrix factorization via fully homomorphic encryption: Extended abstract","authors":"Kim","year":"2016","venue":"Proceedings of the 11th ACM on Asia Conference on Computer and Communications Security","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Koren et al., 2009] Yehuda Koren, Robert Bell, and Chris Volinsky. Matrix factorization techniques for recom- mender systems. Computer, 42(8), 2009.","title":"Matrix factorization techniques for recommender systems","authors":"Koren","year":"2009","venue":"Computer","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Liu et al., 2017] Jian Liu, Mika Juuti, Yao Lu, and N Asokan. Oblivious neural network predictions via min- ionn transformations. In Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, pages 619-631. ACM, 2017.","title":"Oblivious neural network predictions via minionn transformations","authors":"Jian Liu, Mika Juuti, Yao Lu, Asokan","year":"2017","venue":"Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[McSherry and Ilya, 2009] Frank McSherry and Mironov Ilya. Differentially private recommender systems: build- ing privacy into the Netflix prize contenders. In Proceed- ings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 627-636, 2009.","title":"Differentially private recommender systems: building privacy into the Netflix prize contenders","authors":"Ilya Mcsherry, Frank Mcsherry, Mironov Ilya","year":"2009","venue":"Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Nayak et al., 2015] Kartik Nayak, Xiao Shaun Wang, Stratis Ioannidis, Udi Weinsberg, Nina Taft, and Elaine Shi. Graphsc: Parallel secure computation made easy. In Security and Privacy, IEEE Symposium on. IEEE, 2015.","title":"Graphsc: Parallel secure computation made easy","authors":"Kartik Nayak, Xiao, Shaun Wang, Stratis Ioannidis, Udi Weinsberg, Nina Taft, Elaine Shi","year":"2015","venue":"Security and Privacy, IEEE Symposium on","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Netflix, 2010] Netflix. Netflix Prize Dataset, 2010.","title":"Netflix. Netflix Prize Dataset","authors":"Netflix","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Nikolaenko et al., 2013] Valeria Nikolaenko, Ioannidis Stratis, Weinsberg Udi, Joye Marc, Taft Nina, and Boneh Dan. Privacy-preserving matrix factorization. In Proceed- ings of the 2013 ACM SIGSAC Conference on Computer & Communications Security, pages 801-812, 2013.","title":"Privacy-preserving matrix factorization","authors":"Valeria Nikolaenko, Ioannidis Stratis, Weinsberg Udi, Joye Marc, Taft Nina, Boneh Dan","year":"2013","venue":"Proceedings of the 2013 ACM SIGSAC Conference on Computer & Communications Security","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Paillier, 1999] Pascal Paillier. Public-key cryptosystems based on composite degree residuosity classes. In Ad- vances in cryptology-EUROCRYPT. Springer, 1999.","title":"Public-key cryptosystems based on composite degree residuosity classes","authors":"Pascal Paillier","year":"1999","venue":"Advances in cryptology-EUROCRYPT","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ramakrishnan et al., 2001] Naren Ramakrishnan, Ben- jamin J. Keller, Batul J. Mirza, and Ananth Y. Grama. Privacy risks in recommender systems. Internet Comput- ing, IEEE, 5:54-63, 2001.","title":"Privacy risks in recommender systems","authors":"Naren Ramakrishnan, Benjamin J Keller, J Batul, Ananth Y Mirza, Grama","year":"2001","venue":"Internet Computing, IEEE","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Rouhani et al., 2017] Bita Darvish Rouhani, M Sadegh Riazi, and Farinaz Koushanfar. Deepsecure: Scal- able provably-secure deep learning. arXiv preprint arXiv:1705.08963, 2017.","title":"Deepsecure: Scalable provably-secure deep learning","authors":"M Bita Darvish Rouhani, Farinaz Sadegh Riazi, Koushanfar","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Sedhain et al., 2015] Suvash Sedhain, Aditya Krishna Menon, Scott Sanner, and Lexing Xie. Autorec: Autoen- coders meet collaborative filtering. In In International Conference on World Wide Web. ACM, 2015.","title":"Autorec: Autoencoders meet collaborative filtering","authors":"Sedhain","year":"2015","venue":"International Conference on World Wide Web","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Shmueli and Tassa, 2017] Erez Shmueli and Tamir Tassa. Secure multi-party protocols for item-based collaborative filtering. In Proceedings of the Eleventh ACM Conference on Recommender Systems, pages 89-97. ACM, 2017.","title":"Secure multi-party protocols for item-based collaborative filtering","authors":"Tassa Shmueli, Erez Shmueli, Tamir Tassa","year":"2017","venue":"Proceedings of the Eleventh ACM Conference on Recommender Systems","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Su and Khoshgoftaar, 2009] Xiaoyuan Su and Taghi M Khoshgoftaar. A survey of collaborative filtering tech- niques. Advances in artificial intelligence, 2009, 2009.","title":"A survey of collaborative filtering techniques","authors":"Xiaoyuan Su, M Taghi, Khoshgoftaar","year":"2009","venue":"Advances in artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Van Leeuwen, 1976] Jan Van Leeuwen. On the construction of huffman trees. In ICALP, pages 382-410, 1976.","title":"On the construction of huffman trees","authors":"; Van Leeuwen, Jan Van Leeuwen","year":"1976","venue":"ICALP","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yahoo!, 2010] Yahoo! R4-Yahoo! Movies, 2010.","title":"Yahoo! R4-Yahoo! Movies","authors":null,"year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhang et al., 2017] Shuai Zhang, Lina Yao, Aixin Sun, and Tay Yi. Deep learning based recommender sys- tem: A survey and new perspectives. arXiv preprint arXiv:1707.07435, 2017.","title":"Deep learning based recommender system: A survey and new perspectives","authors":"Shuai Zhang, Lina Yao, Aixin Sun, Tay Yi","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhang et al., 2018] Qiao Zhang, Wang Cong, Wu Hongyi, Xin Chunsheng, and Tran V. Phuong. Gelu-net: A globally encrypted, locally unencrypted deep neural network for privacy-preserved learning. In IJCAI, pages 3933-3939, 2018.","title":"Gelu-net: A globally encrypted, locally unencrypted deep neural network for privacy-preserved learning","authors":"Qiao Zhang, Wang Cong, Wu Hongyi, Xin Chunsheng, Tran V Phuong","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/547"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}