Mehmet KOÇ, Burcu Demirelli OKKALIOĞLU, Hüseyin POLAT

Bölünmüş veri-tabanlı gizliliği koruyan ortak filtreleme sistemlerinde gizli verinin elde edilmesi

Ortak filtreleme algoritmalarının doğru ve güvenilir öneriler üretebilmesi için yeterli veriye ihtiyaç vardır. Bu nedenle yetersiz veriye sahip iki elektronik alışveriş sitesi gizliliklerini ihlal etmeden aralarındaki bölünmüş veriden öneriler sunmak isteyebilir. Bu amaçla gizliliği koruyan ortak filtreleme sistemleri geliştirilmiştir. Gizlilik-tabanlı ortak filtreleme sistemlerine karşı ataklar yapılarak gizli veri elde edilebilir. Bu çalışmada yatay ve dikey bölünmüş veri temelli gizliliği koruyan ortak filtreleme sistemlerine karşı atak senaryoları tasarlanıp ne kadar gizli veri elde edilebileceği gösterilmiştir. Ayrıca sistem hakkındaki ilave bilginin gizli veri elde etmeye katkısı çalışılmıştır. Gerçek verilerle yapılan deneyler bazı durumlarda gizli verinin önemli oranda elde edilebileceğini göstermiştir. Fakat ilave bilgi olmadan ve verinin yoğun olduğu durumlarda başarının çok düştüğü gözlenmiştir.

Deriving private data in partitioned data-based privacy-preserving collaborative filtering systems

Collaborative filtering algorithms need enough data to provide accurate and reliable predictions. Hence, two e-commerce sites holding insufficient data may want to provide predictions on their partitioned data with privacy. Different privacy-preserving collaborative filtering systems have been proposed for this purpose. Some attacks can be employed against such systems to derive confidential data. In this paper, attack scenarios are designed against horizontally and vertically partitioned data-based collaborative filtering with privacy schemes to show how much data can be derived. Also, how additional knowledge about the system helps data reconstruction is studied. Empirical outcomes on real data sets show that it is possible to derive high amount of private data in some cases. However, when there is no additional information and data is dense, data reconstruction success becomes very low.

PDF

___

1. Avcı E., Tuncer T., Avcı D., İkili imgeler için mayın tarlası oyunu tabanlı yeni bir veri gizleme algoritması, Journal of the Faculty of Engineering and Architecture of Gazi, 31 (4), 951-959, 2016
2. Shi Y., Larson M., Hanjalic A., Collaborative Filtering Beyond the User-Item Matrix: A Survey of the State of the Art and Future Challenges. ACM Comput. Surv. 47 (1), 1-45, 2014.
3. Koren Y., Bell R., Advances in Collaborative Filtering, Recommender Systems Handbook, Editör: Ricci, F., Rokach, L., Shapira, B., Springer US, Boston, MA, 77- 118, 2015.
4. Canny J., Collaborative filltering with privacy via factor analysis, Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Tampere, Finland, 238-245, 11-15 Ağustos, 2002.
5. Cranor L.F., I didn't buy it for myself': Privacy and ecommerce personalization, Proceedings of the 2003 ACM Workshop on Privacy in the Electronic Society, Washington, DC, USA, 111-117, 27-30 Ekim, 2003.
6. Bilge A., Polat H., A Comparison of Clustering-based Privacy-preserving Collaborative Filtering Schemes. Appl. Soft Comput. 13 (5), 2478-2489, 2013.
7. Li D., Chen C., Lv Q., Shang L., Zhao Y., Lu T., Gu N., An algorithm for efficient privacy-preserving itembased collaborative filtering. Futur. Gener. Comput. Syst. 55, 311-320, 2016.
8. Bilge A., Kaleli C., Yakut I., Gunes I., Polat H., A survey of privacy-preserving collaborative filltering schemes, Int. J. Software Eng. Knowl. Eng., 23 (8), 1085-1108, 2013.
9. Okkalioglu M., Koc M., Polat H., On the privacy of horizontally partitioned binary data-based privacypreserving collaborative filtering, Lect. Notes Comput. Sci., 9481, 199-214, 2015.
10. Okkalioglu M., Koc M., Polat H., A Privacy Review of Vertically Partitioned Data-based PPCF Schemes, International Journal of Information Security Science, 5 (3), 51-68, 2016.
11. Zhang S., Ford J., Makedon, F., Deriving private information from randomly perturbed ratings, Proceedings of the 6th SIAM International Conference on Data Mining, Bethesda, MD, USA, 59-69, 20-26 Nisan, 2006.
12. Okkalioglu M., Koc M., Polat H., On the discovery of fake binary ratings, Proceedings of the 30th Annual ACM Symposium on Applied Computing, Salamanca, Spain, 901-907, 13-17 Nisan, 2015.
13. Demirelli Okkalioglu B., Koc M., Polat H., Reconstructing rated items from perturbed data, Neurocomputing, 207, 374-386, 2016.
14. Okkalioglu B.D., Okkalioglu M., Koc M., Polat H., A survey: Deriving private information from perturbed data, Artificial Intelligence Review, 44 (4), 547-569, 2015.
15. Kargupta H., Datta S., Wang Q., Sivakumar K., Random-data perturbation techniques and privacypreserving data mining, Knowledge and Information Systems, 7 (4), 387-414, 2005.
16. Huang Z., Du W., Chen B., Deriving private information from randomized data, Proceedings of the 24th ACM SIGMOD International Conference on Management of Data, Baltimore, MD, USA, 37-48, 14- 16 Haziran, 2005.
17. Guo S., Wu X., Li, Y., Determining error bounds for spectral filtering based reconstruction methods in privacy preserving data mining, Knowledge and Information Systems, 17 (2), 217-240, 2008.
18. Polat H., Du W., Privacy-preserving collaborative filtering using randomized perturbation techniques, Proceedings of the 3rd IEEE International Conference on Data Mining, Melbourne, FL, USA, 625-628, 19-22 Kasım, 2003.
19. Calandrino J.A., Kilzer A., Narayanan A., Felten E.W., Shmatikov V., You might also like: Privacy risks of collaborative filtering, Proceedings of the 2011 IEEE Symposium on Security and Privacy, Oakland, CA, USA, 231-246, 22-25 Mayıs, 2011.
20. Polat H., Du W., Privacy-preserving top-n recommendation on horizontally partitioned data, Proceedings of the 2005 IEEE/WIC/ACM International Conference on Web Intelligence, Compiègne, France, 725-731, 19-22 Eylül, 2005.
21. Polat H., Du W., Privacy-preserving top-n recommendation on distributed data, Journal of the American Society for Information Science and Technology, 59 (7), 1093-1108, 2008.
22. Polat H., Privacy-preserving collaborative filtering, Doktora Tezi, Syracuse University, Computer and Information Science, Syracuse, NY, 2006.
23. Polat H., Du W., Privacy-preserving collaborative filtering on vertically partitioned data, Lect. Notes Comput. Sci., 3721, 651-658, 2005.
24. Polat H., Du W., Achieving private recommendations using randomized response techniques, Lect. Notes Comput. Sci., 3918, 637-646, 2006.