Are We There Yet? Timing and Floating-Point Attacks on Differential Privacy Systems
暂无分享,去创建一个
[1] Stefano Braghin,et al. Secure Random Sampling in Differential Privacy , 2021, ESORICS.
[2] Martin T. Vechev,et al. DP-Sniper: Black-Box Discovery of Differential Privacy Violations using Classifiers , 2021, 2021 IEEE Symposium on Security and Privacy (SP).
[3] P. Kairouz,et al. The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation , 2021, ICML.
[4] Debdeep Mukhopadhyay,et al. Compact and Secure Generic Discrete Gaussian Sampler based on HW/SW Co-design , 2020, 2020 Asian Hardware Oriented Security and Trust Symposium (AsianHOST).
[5] Thomas Steinke,et al. The Discrete Gaussian for Differential Privacy , 2020, NeurIPS.
[6] Christina Ilvento,et al. Implementing the Exponential Mechanism with Base-2 Differential Privacy , 2019, CCS.
[7] Weijie J. Su,et al. Deep Learning with Gaussian Differential Privacy , 2019, Harvard data science review.
[8] Wouter Joosen,et al. Timeless Timing Attacks: Exploiting Concurrency to Leak Secrets over Remote Connections , 2020, USENIX Security Symposium.
[9] Calton Pu,et al. Differentially Private Model Publishing for Deep Learning , 2019, 2019 IEEE Symposium on Security and Privacy (SP).
[10] Janardhan Kulkarni,et al. An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processors , 2018, NeurIPS.
[11] Frederik Vercauteren,et al. Constant-Time Discrete Gaussian Sampling , 2018, IEEE Transactions on Computers.
[12] Timon Gehr,et al. DP-Finder: Finding Differential Privacy Violations by Sampling and Optimization , 2018, CCS.
[13] John M. Abowd,et al. The U.S. Census Bureau Adopts Differential Privacy , 2018, KDD.
[14] Thomas Steinke,et al. Composable and versatile privacy via truncated CDP , 2018, STOC.
[15] Meng Wu,et al. Eliminating timing side-channel leaks using program repair , 2018, ISSTA.
[16] Danfeng Zhang,et al. Detecting Violations of Differential Privacy , 2018, CCS.
[17] Yu-Xiang Wang,et al. Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising , 2018, ICML.
[18] Ayesha Khalid,et al. On Practical Discrete Gaussian Samplers for Lattice-Based Cryptography , 2018, IEEE Transactions on Computers.
[19] H. Brendan McMahan,et al. Learning Differentially Private Recurrent Language Models , 2017, ICLR.
[20] Salil P. Vadhan,et al. Differential Privacy on Finite Computers , 2017, ITCS.
[21] Dawn Xiaodong Song,et al. Towards Practical Differential Privacy for SQL Queries , 2017, Proc. VLDB Endow..
[22] Úlfar Erlingsson,et al. Prochlo: Strong Privacy for Analytics in the Crowd , 2017, SOSP.
[23] Daniele Micciancio,et al. Gaussian Sampling over the Integers: Efficient, Generic, Constant-Time , 2017, CRYPTO.
[24] Ilya Mironov,et al. Rényi Differential Privacy , 2017, 2017 IEEE 30th Computer Security Foundations Symposium (CSF).
[25] Tanja Lange,et al. Flush, Gauss, and reload : a cache attack on the BLISS lattice-based signature scheme , 2016 .
[26] Ian Goodfellow,et al. Deep Learning with Differential Privacy , 2016, CCS.
[27] Guy N. Rothblum,et al. Concentrated Differential Privacy , 2016, ArXiv.
[28] Dale Miller,et al. Preserving differential privacy under finite-precision semantics , 2013, Theor. Comput. Sci..
[29] Sorin Lerner,et al. On Subnormal Floating Point and Abnormal Timing , 2015, 2015 IEEE Symposium on Security and Privacy.
[30] Alexander J. Smola,et al. Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo , 2015, ICML.
[31] János Folláth. Gaussian Sampling in Lattice Based Cryptography , 2014 .
[32] Aaron Roth,et al. The Algorithmic Foundations of Differential Privacy , 2014, Found. Trends Theor. Comput. Sci..
[33] Raef Bassily,et al. Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds , 2014, 1405.7085.
[34] Andreas Haeberlen,et al. Differential Privacy: An Economic Method for Choosing Epsilon , 2014, 2014 IEEE 27th Computer Security Foundations Symposium.
[35] Anand D. Sarwate,et al. Stochastic gradient descent with differentially private updates , 2013, 2013 IEEE Global Conference on Signal and Information Processing.
[36] Léo Ducas,et al. Lattice Signatures and Bimodal Gaussians , 2013, IACR Cryptol. ePrint Arch..
[37] Chris Peikert,et al. On Ideal Lattices and Learning with Errors over Rings , 2010, JACM.
[38] Ilya Mironov,et al. On significance of the least significant bits for differential privacy , 2012, CCS.
[39] Bart Coppens,et al. Compiler mitigations for time attacks on modern x86 processors , 2012, TACO.
[40] Andreas Haeberlen,et al. Differential Privacy Under Fire , 2011, USENIX Security Symposium.
[41] Danfeng Zhang,et al. Predictive black-box mitigation of timing channels , 2010, CCS '10.
[42] Hovav Shacham,et al. Hey, you, get off of my cloud: exploring information leakage in third-party compute clouds , 2009, CCS.
[43] Frank McSherry,et al. Privacy integrated queries: an extensible platform for privacy-preserving data analysis , 2009, SIGMOD Conference.
[44] Wayne Luk,et al. A hardware Gaussian noise generator using the Box-Muller method and its error analysis , 2006, IEEE Transactions on Computers.
[45] Cynthia Dwork,et al. Calibrating Noise to Sensitivity in Private Data Analysis , 2006, TCC.
[46] G. Marsaglia,et al. The Ziggurat Method for Generating Random Variables , 2000 .
[47] T. A. Bray,et al. A Convenient Method for Generating Normal Variables , 1964 .
[48] G. Marsaglia. Generating a Variable from the Tail of the Normal Distribution , 1964 .