Differentially Private Distributed Learning

References

• Abadi M, Chu A, Goodfellow I, McMahan HB, Mironov I, Talwar K, Zhang L (2016) Deep learning with differential privacy. Proc. 2016 ACM SIGSAC Conf. Comput. Comm. Security (ACM, New York), 308–318.Google Scholar
• Ács G, Castelluccia C (2011) I have a dream! (differentially private smart metering). International Workshop on Information Hiding (Springer, New York), 118–132.Crossref, Google Scholar
• Castelluccia C, Mykletun E, Tsudik G (2005) Efficient aggregation of encrypted data in wireless sensor networks. 2nd Annual Internat. Conf. Mobile Ubiquitous Systems: Networking Services (ACM, New York), 109–117.Google Scholar
• Damiani A, Vallati M, Gatta R, Dinapoli N, Jochems A, Deist T, Van Soest J, Dekker A, Valentini V (2015) Distributed learning to protect privacy in multi-centric clinical studies. Conf. Artificial Intelligence Medicine Eur. (Springer, New York), 65–75.Google Scholar
• Deist TM, Jochems A, van Soest J, Nalbantov G, Oberije C, Walsh S, Eble M, Bulens P, Coucke P, Dries W, et al.. (2017) Infrastructure and distributed learning methodology for privacy-preserving multi-centric rapid learning healthcare: euroCAT. Clinical Translational Radiation Oncology 4:24–31.Google Scholar
• Dwork C (2006) Differential Privacy (Springer Verlag, Venice, Italy).Crossref, Google Scholar
• Dwork C, Lei J (2009) Differential privacy and robust statistics. Proc. 41st Annual ACM Sympos. Theory Comput. (ACM, New York), 371–380.Google Scholar
• Dwork C, McSherry F, Nissim K, Smith A (2006a) Calibrating noise to sensitivity in private data analysis. 2006 Theory Cryptography Conf. (Springer, Berlin, Heidelberg), 265–284.Google Scholar
• Dwork C, Kenthapadi K, McSherry F, Mironov I, Naor M (2006b) Our data, ourselves: Privacy via distributed noise generation. Annual Internat. Conf. Theory Appl. Cryptographic Techniques, Eurocrypt 2006 (Springer, Berlin, Heidelberg), 486–503.Google Scholar
• Fredrikson M, Jha S, Ristenpart T (2015) Model inversion attacks that exploit confidence information and basic countermeasures. Proc. 22nd ACM SIGSAC Conf. Comput. Comm. Security (ACM, New York), 1322–1333.Google Scholar
• He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. IEEE Internat. Conf. Comput. Vision (ICCV) (IEEE, Piscataway, NJ), 1026–1034.Google Scholar
• Johnson R, Zhang T (2013) Accelerating stochastic gradient descent using predictive variance reduction. Burges CJC, Bottou L, Welling M, Ghahramani Z, Weinberger KQ, eds. Advances in Neural Information Processing Systems, vol. 26 (Curran Associates, Red Hook, NY), 315–323.Google Scholar
• Kairouz P, Oh S, Viswanath P (2017) The composition theorem for differential privacy. IEEE Trans. Inform. Theory 63(6):4037–4049.Google Scholar
• Kasiviswanathan SP, Lee HK, Nissim K, Raskhodnikova S, Smith A (2008) What can we learn privately? 49th Annual IEEE Sympos. Foundations Comput. Sci. (IEEE, Piscataway, NJ), 531–540.Google Scholar
• Li N, Qardaji W, Su D (2012) On sampling, anonymization, and differential privacy or, k-anonymization meets differential privacy. Proc. 7th ACM Sympos. Inform. Comput. Comm. Security (ACM, New York), 32–33.Google Scholar
• McMahan B, Ramage D (2017) Federated learning: Collaborative machine learning without centralized training data. Accessed July 5, 2019, https://ai.googleblog.com/2017/04/federated-learning-collaborative.html.Google Scholar
• McMahan HB, Moore E, Ramage D, Agüera y Arcas B (2016) Federated learning of deep networks using model averaging. Working paper, Google AI, Pittsburgh, PA.Google Scholar
• Nesterov Y (2013) Introductory Lectures on Convex Optimization: A Basic Course, vol. 87 (Springer Science & Business Media, Berlin, Heidelberg).Google Scholar
• Reddi SJ, Hefny A, Sra S, Póczós B, Smola A (2016) Stochastic variance reduction for nonconvex optimization. Proc. Machine Learn. Res. 48:314–323.Google Scholar
• Roux NL, Schmidt M, Bach FR (2012) A stochastic gradient method with an exponential convergence rate for finite training sets. Pereira F, Burges CJC, Bottou L, Weinberger KQ, eds. Advances in Neural Information Processing Systems, vol. 25 (Curran Associates, Red Hook, NY), 2663–2671.Google Scholar
• Shalev-Shwartz S, Zhang T (2013) Stochastic dual coordinate ascent methods for regularized loss. J. Machine Learn. Res. 14(1):567–599.Google Scholar
• Sun Y, Wang X, Tang X (2014) Deep learning face representation from predicting 10,000 classes. IEEE Conf. Comput. Vision Pattern Recognition (CVPR) (IEEE, Piscataway, NJ), 1891–1898.Google Scholar
• Tran K, Hosseini S, Xiao L, Finley T, Bilenko M (2015) Scaling up stochastic dual coordinate ascent. Proc. 21st ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining (ACM, New York), 1185–1194.Google Scholar
• Wang Y, Si C, Wu X (2015) Regression model fitting under differential privacy and model inversion attack. Proc. 24th Internat. Conf. Artificial Intelligence (AAAI Press, Palo Alto, CA), 1003–1009.Google Scholar