Towards Practical Differentially Private Convex Optimization

Building useful predictive models often involves learning from sensitive data. Training models with differential privacy can guarantee the privacy of such sensitive data. For convex optimization tasks, several differentially private algorithms are known, but none has yet been deployed in practice. In this work, we make two major contributions towards practical differentially private convex optimization. First, we present Approximate Minima Perturbation, a novel algorithm that can leverage any off-the-shelf optimizer. We show that it can be employed without any hyperparameter tuning, thus making it an attractive technique for practical deployment. Second, we perform an extensive empirical evaluation of the state-of-the-art algorithms for differentially private convex optimization, on a range of publicly available benchmark datasets, and real-world datasets obtained through an industrial collaboration. We release open-source implementations of all the differentially private convex optimization algorithms considered, and benchmarks on as many as nine public datasets, four of which are high-dimensional.

[1]  Anand D. Sarwate,et al.  Differentially Private Empirical Risk Minimization , 2009, J. Mach. Learn. Res..

[2]  Simon Lacoste-Julien,et al.  Convergence Rate of Frank-Wolfe for Non-Convex Objectives , 2016, ArXiv.

[3]  Vitaly Shmatikov,et al.  Membership Inference Attacks Against Machine Learning Models , 2016, 2017 IEEE Symposium on Security and Privacy (SP).

[4]  Ian Goodfellow,et al.  Deep Learning with Differential Privacy , 2016, CCS.

[5]  Vitaly Shmatikov,et al.  Privacy-preserving deep learning , 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[6]  Úlfar Erlingsson,et al.  RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response , 2014, CCS.

[7]  Philip Wolfe,et al.  An algorithm for quadratic programming , 1956 .

[8]  Raef Bassily,et al.  Private Empirical Risk Minimization, Revisited , 2014, ArXiv.

[9]  Pravesh Kothari,et al.  25th Annual Conference on Learning Theory Differentially Private Online Learning , 2022 .

[10]  Moni Naor,et al.  Our Data, Ourselves: Privacy Via Distributed Noise Generation , 2006, EUROCRYPT.

[11]  Daniel Kifer,et al.  Private Convex Empirical Risk Minimization and High-dimensional Regression , 2012, COLT 2012.

[12]  Rong Jin,et al.  Empirical Risk Minimization for Stochastic Convex Optimization: $O(1/n)$- and $O(1/n^2)$-type of Risk Bounds , 2017, COLT.

[13]  Aleksandar Nikolov,et al.  The geometry of differential privacy: the sparse and approximate cases , 2012, STOC '13.

[14]  Charles Elkan,et al.  Differential Privacy and Machine Learning: a Survey and Review , 2014, ArXiv.

[15]  Martin Jaggi,et al.  Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization , 2013, ICML.

[16]  Sanjoy Dasgupta,et al.  A Probabilistic Analysis of EM for Mixtures of Separated, Spherical Gaussians , 2007, J. Mach. Learn. Res..

[17]  Adam D. Smith,et al.  (Nearly) Optimal Algorithms for Private Online Learning in Full-information and Bandit Settings , 2013, NIPS.

[18]  Vitaly Feldman,et al.  Generalization of ERM in Stochastic Convex Optimization: The Dimension Strikes Back , 2016, NIPS.

[19]  Li Zhang,et al.  Private Empirical Risk Minimization Beyond the Worst Case: The Effect of the Constraint Set Geometry , 2014, ArXiv.

[20]  Martin Jaggi,et al.  An Affine Invariant Linear Convergence Analysis for Frank-Wolfe Algorithms , 2013, 1312.7864.

[21]  Kamalika Chaudhuri,et al.  A Stability-based Validation Procedure for Differentially Private Machine Learning , 2013, NIPS.

[22]  Toniann Pitassi,et al.  Generalization in Adaptive Data Analysis and Holdout Reuse , 2015, NIPS.

[23]  Yin Yang,et al.  Functional Mechanism: Regression Analysis under Differential Privacy , 2012, Proc. VLDB Endow..

[24]  Aaron Roth,et al.  The Algorithmic Foundations of Differential Privacy , 2014, Found. Trends Theor. Comput. Sci..

[25]  Somesh Jha,et al.  Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures , 2015, CCS.

[26]  Martin Jaggi,et al.  On the Global Linear Convergence of Frank-Wolfe Optimization Variants , 2015, NIPS.

[27]  R. Hardwarsing.  Stochastic Gradient Descent with Differentially Private Updates , 2018 .

[28]  Prateek Jain,et al.  (Near) Dimension Independent Risk Bounds for Differentially Private Learning , 2014, ICML.

[29]  Prateek Jain,et al.  Differentially Private Learning with Kernels , 2013, ICML.

[30]  Martin J. Wainwright,et al.  Local privacy and statistical minimax rates , 2013, 2013 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[31]  J. Zilinskas,et al.  Analysis of different norms and corresponding Lipschitz constants for global optimization in multidi , 2007 .

[32]  Jeffrey F. Naughton,et al.  Revisiting Differentially Private Regression: Lessons From Learning Theory and their Consequences , 2015, ArXiv.

[33]  Jeffrey F. Naughton,et al.  Bolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics , 2016, SIGMOD Conference.

[34]  Sébastien Bubeck,et al.  Convex Optimization: Algorithms and Complexity , 2014, Found. Trends Mach. Learn..

[35]  Jeffrey F. Naughton,et al.  A Methodology for Formalizing Model-Inversion Attacks , 2016, 2016 IEEE 29th Computer Security Foundations Symposium (CSF).

[36]  Raef Bassily,et al.  Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds , 2014, 1405.7085.

[37]  Cynthia Dwork,et al.  Calibrating Noise to Sensitivity in Private Data Analysis , 2006, TCC.

[38]  Adam D. Smith,et al.  Differentially Private Feature Selection via Stability Arguments, and the Robustness of the Lasso , 2013, COLT.