Dynamic Differential Privacy for ADMM-Based Distributed Classification Learning

IEEE Transactions on Information Forensics and Security

Volumn 12, Issue 1, 2017, Pages 172-187

  Zhang, Tao ^a   Zhu, Quanyan ^a  

^a POLYTECHNIC UNIVERSITY   (United States)

Author keywords

ADMM; differential privacy; distributed computing; dynamic programming; Machine learning; privacy

Indexed keywords

ARTIFICIAL INTELLIGENCE; DATA PRIVACY; DISTRIBUTED COMPUTER SYSTEMS; DYNAMIC PROGRAMMING; DYNAMICS; LEARNING SYSTEMS;

ADMM; ALTERNATING DIRECTION METHOD OF MULTIPLIERS; DIFFERENTIAL PRIVACIES; DISTRIBUTED CLASSIFICATION; DISTRIBUTED LEARNING ALGORITHMS; DISTRIBUTED MACHINE LEARNING; EMPIRICAL RISK MINIMIZATION; MACHINE LEARNING PROBLEM;

LEARNING ALGORITHMS;

EID: 85020567479     PISSN: 15566013     EISSN: None     Source Type: Journal    
DOI: 10.1109/TIFS.2016.2607691     Document Type: Article

References (24)

1. M. Li et al., "Scaling distributed machine learning with the parameter server, " in Proc. OSDI, 2014, pp. 583-598.
2. C. Dwork, F. McSherry, K. Nissim, and A. Smith, "Calibrating noise to sensitivity in private data analysis, " in Theory Cryptography, Berlin, Germany: Springer, 2006, pp. 265-284.
3. K. Nissim, S. Raskhodnikova, and A. Smith, "Smooth sensitivity and sampling in private data analysis, " in Proc. 39th Annu. ACM Symp. Theory Comput., 2007, pp. 75-84.
4. J. Dean and S. Ghemawat, "MapReduce: Simplified data processing on large clusters, " Commun. ACM, vol. 51, no. 1, pp. 107-113, 2008.
5. P. A. Forero, A. Cano, and G. B. Giannakis, "Consensus-based distributed support vector machines, " J. Mach. Learn. Res., vol. 11, pp. 1663-1707, Jan. 2010.
6. M. Collins, "Discriminative training methods for hidden Markov models: Theory and experiments with perceptron algorithms, " in Proc. Conf. Empirical Methods Natural Lang. Process, 2002, pp. 1-8.
7. R. McDonald, K. Hall, and G. Mann, "Distributed training strategies for the structured perceptron, " in Proc. Human Lang. Technol. Annu. Conf. North Amer. Chapter Assoc. Comput. Linguistics, 2010, pp. 456-464.
8. A. Evfimievski, R. Srikant, R. Agrawal, and J. Gehrke, "Privacy preserving mining of association rules, " Inf. Syst., vol. 29, no. 4, pp. 343-364, Jun. 2004.
9. J. Kim and W. Winkler, "Multiplicative noise for masking continuous data, " Statistics, 2003, pp. 1-6.
10. L. G. Valiant, "A theory of the learnable, " Commun. ACM, vol. 27, no. 11, pp. 1134-1142, 1984.
11. S. P. Kasiviswanathan, H. K. Lee, K. Nissim, S. Raskhodnikova, and A. Smith, "What can we learn privately?" SIAM J. Comput., vol. 40, no. 3, pp. 793-826, Jun. 2011. [Online]. Available: Http://dx.doi. org/10.1137/090756090
12. F. McSherry and K. Talwar, "Mechanism design via differential privacy, " in Proc. 48th Annu. IEEE Symp. Found. Comput. Sci., 2007, pp. 94-103.
13. A. Blum, C. Dwork, and K. Nissim, "Practical privacy: The sulq framework, " in Proc. 24th ACM SIGMOD-SIGACT-SIGART Symp. Principles Database Syst., 2005, pp. 128-138.
14. R. Chen, A. Reznichenko, P. Francis, and J. Gehrke, "Towards statistical queries over distributed private user data, " presented at the 9th USENIX Symp. Netw. Syst. Design Implement. (NSDI), 2012, pp. 169-182.
15. I. Mironov, O. Pandey, O. Reingold, and S. Vadhan, "Computational differential privacy, " in Advances in Cryptology-CRYPTO, Berlin, Germany: Springer, 2009, pp. 126-142.
16. F. Eigner and M. Maffei, "Differential privacy by typing in security protocols, " in Proc. IEEE 26th Comput. Secur. Found. Symp. (CSF), 2013, pp. 272-286.
17. Y.-H. Dai, "A perfect example for the bfgs method, " Math. Program., vol. 138, no. 1, pp. 501-530, Apr. 2013.
18. S. Shalev-Shwartz and N. Srebro, "Svm optimization: Inverse dependence on training set size, " in Proc. 25th Int. Conf. Mach. Learn., 2008, pp. 928-935.
19. K. Chaudhuri, C. Monteleoni, and A. D. Sarwate, "Differentially private empirical risk minimization, " J. Mach. Learn. Res., vol. 12, pp. 1069-1109, Mar. 2011.
20. A. Asuncion and D. Newman, "UCI machine learning repository, " Dept. School Inf. Comput. Sci., Univ. California, Irvine, Irvine, CA, USA, Tech. Rep., 2007.
21. A. Narayanan and V. Shmatikov, "Robust de-anonymization of large sparse datasets, " in Proc. IEEE Symp. Secur. Privacy, 2008, pp. 111-125.
22. P. Chilstrom, "Singular value inequalities: New approaches to conjectures, " M.S. thesis, Dept. Math. Statist. Univ. North Florida, Jacksonville, FL. USA, 2013.
23. S. Shalev-Shwartz and Y. Singer, Online Learning: Theory, Algorithms, and Applications. Jerusalem, Israel: Senate of the Hebrew Univ., 2007.
24. K. Sridharan, S. Shalev-Shwartz, and N. Srebro, "Fast rates for regularized objectives, " in Proc. Adv. Neural Inf. Process. Syst., 2009, pp. 1545-1552.