USST: a two-phase privacy-preserving framework for personalized recommendation with semi-distributed training. (English) Zbl 07814165
Summary: Personalized recommendations are becoming indispensable for assisting online users in discovering items of interest. However, existing recommendation algorithms rely heavily on the collection of personal information, which poses significant privacy concerns to users. In this paper, we propose a two-phase privacy-preserving framework called user sampling and semi-distributed training (USST) for personalized recommendations, which can protect user privacy while ensuring high recommendation accuracy. In the USST framework, rather than directly training the model with all user records, a shared model is first trained with a small set of records contributed by sampled users (e.g., paid users and volunteers). This shared model is then distributed to each user, who further trains a personalized model using personal information. Thus, the USST guarantees that all unsampled users never disclose their private information. To validate the effectiveness and practicality of USST, we designed two USST-based privacy-preserving recommendation algorithms, USST-SVD and USST-NCF based on SVD and NCF algorithms, respectively. We conducted evaluations using MovieLens and Netflix Prize datasets, and the results show that, using only 20% of sampled users’ records, the recommendation accuracy of USST-based algorithms is very close to that of all users’ records. Thus, USST can significantly improve the level of privacy protection in recommender systems.
MSC:
| 68T35 | Theory of languages and software systems (knowledge-based systems, expert systems, etc.) for artificial intelligence |
| 68P27 | Privacy of data |
References:
| [1] | Anelli, V. W.; Belli, L.; Deldjoo, Y.; Di Noia, T.; Ferrara, A.; Narducci, F.; Pomo, C., Pursuing privacy in recommender systems: the view of users and researchers from regulations to applications, (Fifteenth ACM Conference on Recommender Systems (2021)), 838-841 |
| [2] | Anelli, V. W.; Deldjoo, Y.; Di Noia, T.; Ferrara, A.; Narducci, F., How to put users in control of their data in federated top-n recommendation with learning to rank, (Proceedings of the 36th Annual ACM Symposium on Applied Computing (2021)), 1359-1362 |
| [3] | Anelli, V.W., Deldjoo, Y., Noia, T.D., Ferrara, A., Narducci, F., 2021c. Federank: User controlled feedback with federated recommender systems. In: European Conference on Information Retrieval. Springer, pp. 32-47. |
| [4] | Belli, L., Ktena, S.I., Tejani, A., Lung-Yut-Fon, A., Portman, F., Zhu, X., Xie, Y., Gupta, A., Bronstein, M., Delić, A., et al., 2020. Privacy-aware recommender systems challenge on twitter’s home timeline. arXiv preprint arXiv:2004.13715. |
| [5] | Berlioz, A.; Friedman, A.; Kaafar, M. A.; Boreli, R.; Berkovsky, S., Applying differential privacy to matrix factorization, (Proceedings of the 9th ACM Conference on Recommender Systems (2015)), 107-114 |
| [6] | Burbach, L.; Nakayama, J.; Plettenberg, N.; Ziefle, M.; Valdez, A. C., User preferences in recommendation algorithms: the influence of user diversity, trust, and product category on privacy perceptions in recommender algorithms, (Proceedings of the 12th ACM conference on recommender systems (2018)), 306-310 |
| [7] | Chai, D.; Wang, L.; Chen, K.; Yang, Q., Secure federated matrix factorization, IEEE Intelligent Systems (2020) |
| [8] | Chen, C.; Liu, Z.; Zhao, P.; Zhou, J.; Li, X., Privacy preserving point-of-interest recommendation using decentralized matrix factorization, (Thirty-Second AAAI Conference on Artificial Intelligence (2018)) |
| [9] | Dareddy, M.R., Das, A., Cho, J., Zaniolo, C., 2018. How much are you willing to share? a poker-styled selective privacy preserving framework for recommender systems. arXiv preprint arXiv:1806.00914. |
| [10] | Ding, W.; Yan, Z.; Deng, R. H., Encrypted data processing with homomorphic re-encryption, Information Sciences, 409, 35-55 (2017) · Zbl 1429.68060 |
| [11] | Duriakova, E.; Tragos, E. Z.; Smyth, B.; Hurley, N.; Peña, F. J.; Symeonidis, P.; Geraci, J.; Lawlor, A., Pdmfrec: a decentralised matrix factorisation with tunable user-centric privacy, (Proceedings of the 13th ACM Conference on Recommender Systems (2019)), 457-461 |
| [12] | Dwork, C.; Roth, A., The algorithmic foundations of differential privacy, Foundations and Trends in Theoretical Computer Science, 9, 3-4, 211-407 (2014) · Zbl 1302.68109 |
| [13] | Friedman, A.; Berkovsky, S.; Kaafar, M. A., A differential privacy framework for matrix factorization recommender systems, User Modeling and User-Adapted Interaction, 26, 5, 425-458 (2016) |
| [14] | Fung, C., Yoon, C.J., Beschastnikh, I., 2018. Mitigating sybils in federated learning poisoning. arXiv preprint arXiv:1808.04866. |
| [15] | Gao, D., Tan, B., Ju, C., Zheng, V.W., Yang, Q., 2020. Privacy threats against federated matrix factorization. arXiv preprint arXiv:2007.01587. |
| [16] | Guo, T.; Luo, J.; Dong, K.; Yang, M., Locally differentially private item-based collaborative filtering, Information Sciences, 502, 229-246 (2019) · Zbl 1453.68071 |
| [17] | Gursoy, M. E.; Tamersoy, A.; Truex, S.; Wei, W.; Liu, L., Secure and utility-aware data collection with condensed local differential privacy, IEEE Transactions on Dependable and Secure Computing (2019) |
| [18] | He, X.; Liao, L.; Zhang, H.; Nie, L.; Hu, X.; Chua, T.-S., Neural collaborative filtering, (Proceedings of the 26th international conference on world wide web. International World Wide Web Conferences Steering Committee (2017)), 173-182 |
| [19] | He, X.; Zhang, H.; Kan, M.-Y.; Chua, T.-S., Fast matrix factorization for online recommendation with implicit feedback, (Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval (2016)), 549-558 |
| [20] | Hitaj, B.; Ateniese, G.; Perez-Cruz, F., Deep models under the gan: information leakage from collaborative deep learning, (Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security. ACM (2017)), 603-618 |
| [21] | Jayaraman, B.; Evans, D., Evaluating differentially private machine learning in practice, (28th USENIX Security Symposium (USENIX Security 19) (2019), USENIX Association: USENIX Association Santa Clara, CA) |
| [22] | Jiang, J.-Y.; Li, C.-T.; Lin, S.-D., Towards a more reliable privacy-preserving recommender system, Information Sciences, 482, 248-265 (2019) |
| [23] | Jiang, Y.; Zhou, Y.; Wu, D.; Li, C.; Wang, Y., On the detection of shilling attacks in federated collaborative filtering, (2020 International Symposium on Reliable Distributed Systems (SRDS) (2020), IEEE), 185-194 |
| [24] | Kairouz, P., McMahan, H.B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A.N., Bonawitz, K., Charles, Z., Cormode, G., Cummings, R., et al., 2019. Advances and open problems in federated learning. arXiv preprint arXiv:1912.04977. |
| [25] | Knijnenburg, B. P.; Berkovsky, S., Privacy for recommender systems: tutorial abstract, (Proceedings of the Eleventh ACM Conference on Recommender Systems (2017)), 394-395 |
| [26] | Li, D.; Chen, C.; Lv, Q.; Shang, L.; Zhao, Y.; Lu, T.; Gu, N., An algorithm for efficient privacy-preserving item-based collaborative filtering, Future Generation Computer Systems, 55, 311-320 (2016) |
| [27] | Liu, A.; Yao, Y.; Cheng, X., Recommender systems with condensed local differential privacy, (International Conference on Machine Learning for Cyber Security (2020), Springer), 355-365 |
| [28] | Liu, B.; Ding, M.; Shaham, S.; Rahayu, W.; Farokhi, F.; Lin, Z., When machine learning meets privacy: A survey and outlook, ACM Computing Surveys (CSUR), 54, 2, 1-36 (2021) |
| [29] | Narayanan, A.; Shmatikov, V., Robust de-anonymization of large datasets (how to break anonymity of the netflix prize dataset) (2008), University of Texas at Austin |
| [30] | Nasr, M., Shokri, R., Houmansadr, A., 2018. Comprehensive privacy analysis of deep learning: Stand-alone and federated learning under passive and active white-box inference attacks. arXiv preprint arXiv:1812.00910. |
| [31] | Oh, J.; Kim, S.; Kim, J.; Yu, H., When to recommend: A new issue on tv show recommendation, Information Sciences, 280, 261-274 (2014) |
| [32] | Ran, X.; Wang, Y.; Zhang, L. Y.; Ma, J., A differentially private nonnegative matrix factorization for recommender system, Information Sciences, 592, 21-35 (2022) · Zbl 1535.68079 |
| [33] | Rao, J. M.; Reiley, D. H., The economics of spam, Journal of Economic Perspectives, 26, 3, 87-110 (2012) |
| [34] | Saini, A.; Rusu, F.; Johnston, A., Privatejobmatch: a privacy-oriented deferred multi-match recommender system for stable employment, (Proceedings of the 13th ACM Conference on Recommender Systems (2019)), 87-95 |
| [35] | Shen, Y.; Jin, H., Epicrec: Towards practical differentially private framework for personalized recommendation, (Proceedings of the 2016 ACM SIGSAC conference on computer and communications security (2016)), 180-191 |
| [36] | Shin, H.; Kim, S.; Shin, J.; Xiao, X., Privacy enhanced matrix factorization for recommendation with local differential privacy, IEEE Transactions on Knowledge and Data Engineering, 30, 9, 1770-1782 (2018) |
| [37] | Shmueli, E.; Tassa, T., Secure multi-party protocols for item-based collaborative filtering, (Proceedings of the eleventh ACM conference on recommender systems (2017)), 89-97 |
| [38] | Tang, Q.; Wang, J., Privacy-preserving friendship-based recommender systems, IEEE Transactions on Dependable and Secure Computing, 15, 5, 784-796 (2016) |
| [39] | Wadhwa, S.; Agrawal, S.; Chaudhari, H.; Sharma, D.; Achan, K., Data poisoning attacks against differentially private recommender systems, (Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (2020)), 1617-1620 |
| [40] | Wahab, O. A.; Rjoub, G.; Bentahar, J.; Cohen, R., Federated against the cold: A trust-based federated learning approach to counter the cold start problem in recommendation systems, Information Sciences (2022) |
| [41] | Wainakh, A.; Grube, T.; Daubert, J.; Mühlhäuser, M., Efficient privacy-preserving recommendations based on social graphs, (Proceedings of the 13th ACM Conference on Recommender Systems (2019)), 78-86 |
| [42] | Wang, F.; Zhu, H.; Lu, R.; Zheng, Y.; Li, H., A privacy-preserving and non-interactive federated learning scheme for regression training with gradient descent, Information Sciences (2020) |
| [43] | Wang, H.; Zhao, Q.; Wu, Q.; Chopra, S.; Khaitan, A.; Wang, H., Global and local differential privacy for collaborative bandits, (Fourteenth ACM Conference on Recommender Systems (2020)), 150-159 |
| [44] | Wang, J., Tang, Q., Arriaga, A., Ryan, P.Y., 2019. Novel collaborative filtering recommender friendly to privacy protection. In: IJCAI. pp. 4809-4815. |
| [45] | Wei, K.; Li, J.; Ding, M.; Ma, C.; Yang, H. H.; Farokhi, F.; Jin, S.; Quek, T. Q.; Poor, H. V., Federated learning with differential privacy: Algorithms and performance analysis, IEEE Transactions on Information Forensics and Security, 15, 3454-3469 (2020) |
| [46] | Wu, Z.; Zhou, Y.; Wu, D.; Chen, M.; Xu, Y., Tamf: towards personalized time-aware recommendation for over-the-top videos, (Proceedings of the 29th ACM Workshop on Network and Operating Systems Support for Digital Audio and Video. ACM (2019)), 43-48 |
| [47] | Xin, Y., Jaakkola, T., 2014. Controlling privacy in recommender systems. In: Advances in neural information processing systems. pp. 2618-2626. |
| [48] | Zhang, J.; Zhou, Y.; Wu, D.; Yang, C., Context-aware video recommendation by mining users’ view preferences based on access points, (Proceedings of the 27th Workshop on Network and Operating Systems Support for Digital Audio and Video (2017), ACM), 37-42 |
| [49] | Zheng, L.; Zhu, F.; Huang, S.; Xie, J., Context neighbor recommender: Integrating contexts via neighbors for recommendations, Information Sciences, 414, 1-18 (2017) |
| [50] | Zhou, H., Liu, X.-Y., Fu, C., Shang, C., Chang, X., 2018. Differentially private matrix completion via distributed matrix factorization. In: 2018 17th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/12th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE). IEEE, pp. 1628-1631. |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
