Supervised Machine Learning with Plausible Deniability

Al-Rubaie, 2019, Privacy-preserving machine learning: Threats and solutions, IEEE Security Privacy, 17, 49, 10.1109/MSEC.2018.2888775 Azencott, 2018, Machine learning and genomics: precision medicine versus patient privacy, Phil Trans R Soc A, 376, 20170350, 10.1098/rsta.2017.0350 Bilogrevic, 2016, A machine-learning based approach to privacy-aware information-sharing in mobile social networks, Pervasive and Mobile Computing, 25, 125, 10.1016/j.pmcj.2015.01.006 Bindschaedler, 2017, Plausible deniability for privacy-preserving data synthesis, Proceedings of the VLDB Endowment, 10, 481, 10.14778/3055540.3055542 Bonawitz Bonawitz, 2017, Practical secure aggregation for privacypreserving machine learning, 1175 Bost, 2015, Machine learning classification over encrypted data Chaudhuri, 2009, Privacy-preserving logistic regression, volume 21, 289 Chen Dwork, 2006, Differential privacy, volume 4052, 1 Eaton J.W., Bateman D., Hauberg S., Wehbring R.. GNU octave version 5.2.0 manual: a high-level interactive language for numerical computations. 2020. URL https://www.gnu.org/software/octave/doc/v5.2.0/. Fredrikson, 2015, Model inversion attacks that exploit confidence information and basic countermeasures, 1322 Fredrikson, 2014, Privacy in pharmacogenetics: an end-to-end case study of personalized warfarin dosing, 17 Fritchman, 2018, 2413 Gadotti, 2019, When the signal is in the noise: Exploiting diffix’s sticky noise, 18 Hidano, 2017, Model inversion attacks for prediction systems: Without knowledge of nonsensitive attributes, 115 Jia, 2019, Efficient privacy-preserving machine learning in hierarchical distributed system, IEEE Transactions on Network Science and Engineering, 6, 599, 10.1109/TNSE.2018.2859420 Jia, 2018, Preserving model privacy for machine learning in distributed systems, IEEE Transactions on Parallel and Distributed Systems, 29, 1808, 10.1109/TPDS.2018.2809624 Junxu, 2020, Survey on privacy-preserving machine learning, Journal of Computer Research and Development, 57, 346 Keras Team. Keras documentation: Losses. 2020. https://keras.io/api/losses/. Li, 2020, Federated learning: Challenges, methods, and future directions, IEEE Signal Processing Magazine, 37, 50, 10.1109/MSP.2020.2975749 Papernot, 2018, Sok: Security and privacy in machine learning, 399 Schauer, 2020, Cross-domain risk analysis to strengthen city resilience: the ODYSSEUS approach, 652 Srishilesh P.S.. Understanding differential privacy. 2020. URL https://www.section.io/engineering-education/understanding-differential-privacy/. Stach, 2020, AMNESIA: A technical solution towards GDPR-compliant machine learning, 21 Till O.. The ’optim’ package. 2019. URL https://octave.sourceforge.io/optim/. Vinterbo, 2004, Privacy: a machine learning view, IEEE Transactions on Knowledge and Data Engineering, 16, 939, 10.1109/TKDE.2004.31 Walter, 1995 Yang, 2019, 13, 1 Zhang, 2017, Dynamic differential privacy for ADMM-based distributed classification learning, IEEE Transactions on Information Forensics and Security, 12, 172, 10.1109/TIFS.2016.2607691