SecureML: A System for Scalable Privacy-Preserving Machine Learning

Proceedings - IEEE Symposium on Security and Privacy

Volumn , Issue , 2017, Pages 19-38

  Mohassel, Payman ^a   Zhang, Yupeng ^b  

^a VISA RESEARCH   (United States)

^b UNIVERSITY OF MARYLAND   (United States)

Author keywords

Privacy preserving machine learning; Secure computation

Indexed keywords

ARTIFICIAL INTELLIGENCE; CHARACTER RECOGNITION; COMMUNICATION CHANNELS (INFORMATION THEORY); EDUCATION; FUNCTIONS; IMAGE PROCESSING; LEARNING SYSTEMS; NEURAL NETWORKS; REGRESSION ANALYSIS; SPEECH RECOGNITION; STOCHASTIC SYSTEMS;

ARITHMETIC OPERATIONS; EFFICIENT PROTOCOLS; LOGISTIC REGRESSIONS; NEURAL NETWORK TRAINING; PRIVACY PRESERVING; SECURE COMPUTATION; SECURE TWO-PARTY COMPUTATIONS; STOCHASTIC GRADIENT DESCENT METHOD;

DATA PRIVACY;

EID: 85024487501     PISSN: 10816011     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/SP.2017.12     Document Type: Conference Paper

References (48)

1. Arcene data set. https://archive. ics. uci. edu/ml/datasets/Arcene. Accessed: 2016-07-14.
2. Eigen library. http://eigen. Tuxfamily. org/.
3. EMP toolkit. https://github. com/emp-toolkit.
4. Gisette data set. https://archive. ics. uci. edu/ml/datasets/Gisette. Accessed: 2016-07-14.
5. GMP library. https://gmplib. org/.
6. MNIST database. http://yann. lecun. com/exdb/mnist/. Accessed: 2016-07-14.
7. NTL library. http://www. shoup. net/ntl/.
8. Tensorflow. https://www. Tensorflow. org/.
9. ABADI, M., CHU, A., GOODFELLOW, I., MCMAHAN, H. B., MIRONOV, I., TALWAR, K., AND ZHANG, L. Deep learning with differential privacy. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (2016), ACM, pp. 308-318.
10. AONO, Y., HAYASHI, T., TRIEU PHONG, L., AND WANG, L. Scalable and secure logistic regression via homomorphic encryption. In Proceedings of the Sixth ACM Conference on Data and Application Security and Privacy (2016), ACM, pp. 142-144.
11. ASHAROV, G., LINDELL, Y., SCHNEIDER, T., AND ZOHNER, M. More efficient oblivious transfer and extensions for faster secure computation. In Proceedings of the ACM CCS 2013 (2013).
12. BELLARE, M., HOANG, V. T., KEELVEEDHI, S., AND ROGAWAY, P. Efficient garbling from a fixed-key blockcipher. In Security and Privacy (SP), 2013 IEEE Symposium on (2013), IEEE, pp. 478-492.
13. BELLARE, M., HOANG, V. T., AND ROGAWAY, P. Foundations of garbled circuits. In Proceedings of the 2012 ACM conference on Computer and communications security (2012), ACM, pp. 784-796.
14. BUNN, P., AND OSTROVSKY, R. Secure two-party k-means clustering. In Proceedings of the 14th ACM conference on Computer and communications security (2007), ACM, pp. 486-497.
15. CANETTI, R. Universally composable security: A new paradigm for cryptographic protocols. In Foundations of Computer Science, 2001. Proceedings. 42nd IEEE Symposium on (2001), IEEE, pp. 136-145.
16. CHAUDHURI, K., AND MONTELEONI, C. Privacy-preserving logistic regression. In Advances in Neural Information Processing Systems (2009), pp. 289-296.
17. DAMGARD, I., GEISLER, M., AND KROIGARD, M. Homomorphic encryption and secure comparison. International Journal of Applied Cryptography 1, 1 (2008), 22-31.
18. DEMMLER, D., SCHNEIDER, T., AND ZOHNER, M. Aby-a framework for efficient mixed-protocol secure two-party computation. In NDSS (2015).
19. DU, W., AND ATALLAH, M. J. Privacy-preserving cooperative scientific computations. In csfw (2001), vol. 1, Citeseer, p. 273.
20. DU, W., HAN, Y. S., AND CHEN, S. Privacy-preserving multivariate statistical analysis: Linear regression and classification. In SDM (2004), vol. 4, SIAM, pp. 222-233.
21. GASCON, A., SCHOPPMANN, P., BALLE, B., RAYKOVA, M., DOERNER, J., ZAHUR, S., AND EVANS, D. Secure linear regression on vertically partitioned datasets.
22. GILAD-BACHRACH, R., DOWLIN, N., LAINE, K., LAUTER, K., NAEHRIG, M., AND WERNSING, J. Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy. In Proceedings of The 33rd International Conference on Machine Learning (2016), pp. 201-210.
23. GILAD-BACHRACH, R., LAINE, K., LAUTER, K., RINDAL, P., AND ROSULEK, M. Secure data exchange: A marketplace in the cloud. Cryptology ePrint Archive, Report 2016/620, 2016. http://eprint. iacr. org/ 2016/620.
24. GILAD-BACHRACH, R., LAINE, K., LAUTER, K., RINDAL, P., AND ROSULEK, M. Secure data exchange: A marketplace in the cloud.
25. GUYON, I., GUNN, S., BEN-HUR, A., AND DROR, G. Result analysis of the nips 2003 feature selection challenge. In Advances in neural information processing systems (2004), pp. 545-552.
26. HASTIE, T., TIBSHIRANI, R., AND FRIEDMAN, J. The elements of statistical learning-data mining, inference, and prediction.
27. ISHAI, Y., KILIAN, J., NISSIM, K., AND PETRANK, E. Extending oblivious transfers efficiently. Advances in Cryptology-CRYPTO 2003 (2003), 145-161.
28. JAGANNATHAN, G., AND WRIGHT, R. N. Privacy-preserving distributed k-means clustering over arbitrarily partitioned data. In Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining (2005), ACM, pp. 593-599.
29. KAMARA, S., MOHASSEL, P., AND RAYKOVA, M. Outsourcing multiparty computation. IACR Cryptology ePrint Archive (2011), 272.
30. KOLESNIKOV, V., AND SCHNEIDER, T. Improved garbled circuit: Free xor gates and applications. In International Colloquium on Automata, Languages, and Programming (2008), Springer, pp. 486-498.
31. LINDELL, Y., AND PINKAS, B. Privacy preserving data mining. In Annual International Cryptology Conference (2000), Springer, pp. 36-54.
32. LINDELL, Y., AND PINKAS, B. A proof of security of yaos protocol for two-party computation. Journal of Cryptology 22, 2 (2009), 161-188.
33. LIVNI, R., SHALEV-SHWARTZ, S., AND SHAMIR, O. On the computational efficiency of training neural networks. In Advances in Neural Information Processing Systems (2014), pp. 855-863.
34. MALKHI, D., NISAN, N., PINKAS, B., SELLA, Y., et al. Fairplaysecure two-party computation system.
35. NAYAK, K., WANG, X. S., IOANNIDIS, S., WEINSBERG, U., TAFT, N., AND SHI, E. Graphsc: Parallel secure computation made easy. In 2015 IEEE Symposium on Security and Privacy (2015), IEEE, pp. 377-394.
36. NIKOLAENKO, V., IOANNIDIS, S., WEINSBERG, U., JOYE, M., TAFT, N., AND BONEH, D. Privacy-preserving matrix factorization. In Proceedings of the 2013 ACM SIGSAC conference on Computer & communications security (2013), ACM, pp. 801-812.
37. NIKOLAENKO, V., WEINSBERG, U., IOANNIDIS, S., JOYE, M., BONEH, D., AND TAFT, N. Privacy-preserving ridge regression on hundreds of millions of records. In Security and Privacy (SP), 2013 IEEE Symposium on (2013), IEEE, pp. 334-348.
38. PAILLIER, P. Public-key cryptosystems based on composite degree residuosity classes. In International Conference on the Theory and Applications of Cryptographic Techniques (1999), Springer, pp. 223-238.
39. PEIKERT, C., VAIKUNTANATHAN, V., AND WATERS, B. A framework for efficient and composable oblivious transfer. Advances in Cryptology-CRYPTO 2008 (2008), 554-571.
40. SANIL, A. P., KARR, A. F., LIN, X., AND REITER, J. P. Privacy preserving regression modelling via distributed computation. In Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining (2004), ACM, pp. 677-682.
41. SHOKRI, R., AND SHMATIKOV, V. Privacy-preserving deep learning. In Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security (2015), ACM, pp. 1310-1321.
42. SLAVKOVIC, A. B., NARDI, Y., AND TIBBITS, M. M. " secure" logistic regression of horizontally and vertically partitioned distributed databases. In Seventh IEEE International Conference on Data Mining Workshops (ICDMW 2007) (2007), IEEE, pp. 723-728.
43. SONG, S., CHAUDHURI, K., AND SARWATE, A. D. Stochastic gradient descent with differentially private updates. In Global Conference on Signal and Information Processing (GlobalSIP), 2013 IEEE (2013), IEEE, pp. 245-248.
44. VAIDYA, J., YU, H., AND JIANG, X. Privacy-preserving svm classification. Knowledge and Information Systems 14, 2 (2008), 161-178.
45. WANG, X., MALOZEMOFF, A. J., AND KATZ, J. Faster two-party computation secure against malicious adversaries in the single-execution setting. Cryptology ePrint Archive, Report 2016/762, 2016. http://eprint. iacr. org/2016/762.
46. WU, S., TERUYA, T., KAWAMOTO, J., SAKUMA, J., AND KIKUCHI, H. Privacy-preservation for stochastic gradient descent application to secure logistic regression. The 27th Annual Conference of the Japanese Society for Artificial Intelligence 27 (2013), 1-4.
47. YAO, A. C. Protocols for secure computations. In Foundations of Computer Science, 1982. SFCS'08. 23rd Annual Symposium on (1982), IEEE, pp. 160-164.
48. YU, H., VAIDYA, J., AND JIANG, X. Privacy-preserving svm classification on vertically partitioned data. In Pacific-Asia Conference on Knowledge Discovery and Data Mining (2006), Springer, pp. 647-656.