On Privacy of Dynamical Systems: An Optimal Probabilistic Mapping Approach

We address the problem of maximizing privacy of stochastic dynamical systems whose state information is released through quantized sensor data. In particular, we consider the setting where information about the system state is obtained using noisy sensor measurements. This data is quantized and transmitted to a remote station through a public/unsecured communication network. We aim at keeping the state of the system private; however, because the network is not secure, adversaries might have access to sensor data, which can be used to estimate the system state. To prevent such adversaries from obtaining an accurate state estimate, before transmission, we randomize quantized sensor data using additive random vectors, and send the corrupted data to the remote station instead. We design the joint probability distribution of these additive vectors (over a time window) to minimize the mutual information (our privacy metric) between some linear function of the system state (a desired private output) and the randomized sensor data for a desired level of distortion--how different quantized sensor measurements and distorted data are allowed to be. We pose the problem of synthesizing the joint probability distribution of the additive vectors as a convex program subject to linear constraints. Simulation experiments are presented to illustrate our privacy scheme.

[1]  Josep Domingo-Ferrer,et al.  Optimal data-independent noise for differential privacy , 2013, Inf. Sci..

[2]  Martín Ochoa,et al.  Design-time Quantification of Integrity in Cyber-physical Systems , 2017, PLAS@CCS.

[3]  Hui Xiong,et al.  Enhancing Security and Privacy in Traffic-Monitoring Systems , 2006, IEEE Pervasive Computing.

[4]  Geir E. Dullerud,et al.  On the cost of differential privacy in distributed control systems , 2014, HiCoNS.

[5]  Stephen P. Boyd,et al.  Linear Matrix Inequalities in Systems and Control Theory , 1994 .

[6]  Navid Hashemi,et al.  A Comparison of Stealthy Sensor Attacks on Control Systems , 2017, 2018 Annual American Control Conference (ACC).

[7]  Henrik Sandberg,et al.  Quadratic Gaussian privacy games , 2015, 2015 54th IEEE Conference on Decision and Control (CDC).

[8]  Sheldon M. Ross,et al.  Introduction to Probability Models, Eighth Edition , 1972 .

[9]  Allen Gersho,et al.  Vector quantization and signal compression , 1991, The Kluwer international series in engineering and computer science.

[10]  Carlos Murguia,et al.  Model-based Attack Detection Scheme for Smart Water Distribution Networks , 2017, AsiaCCS.

[11]  Pramod Viswanath,et al.  The optimal mechanism in differential privacy , 2012, 2014 IEEE International Symposium on Information Theory.

[12]  Cynthia Dwork,et al.  Differential Privacy: A Survey of Results , 2008, TAMC.

[13]  Nina Taft,et al.  Managing Your Private and Public Data: Bringing Down Inference Attacks Against Your Privacy , 2014, IEEE Journal of Selected Topics in Signal Processing.

[14]  Jairo Giraldo,et al.  Constraining Attacker Capabilities Through Actuator Saturation , 2017, 2018 Annual American Control Conference (ACC).

[15]  Stephen J. Wright,et al.  Numerical Optimization , 2018, Fundamental Statistical Inference.

[16]  Ufuk Topcu,et al.  Differentially private convex optimization with piecewise affine objectives , 2014, 53rd IEEE Conference on Decision and Control.

[17]  Florian Dörfler,et al.  Attack Detection and Identification in Cyber-Physical Systems -- Part II: Centralized and Distributed Monitor Design , 2012, ArXiv.

[18]  Witold Pedrycz,et al.  Measuring relevance between discrete and continuous features based on neighborhood mutual information , 2011, Expert Syst. Appl..

[19]  William M. Campbell,et al.  Mutual Information in Learning Feature Transformations , 2000, ICML.

[20]  Charles R. Johnson,et al.  Matrix Analysis, 2nd Ed , 2012 .

[21]  H. Vincent Poor,et al.  Increasing Smart Meter Privacy Through Energy Harvesting and Storage Devices , 2013, IEEE Journal on Selected Areas in Communications.

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

[23]  Carlos Murguia,et al.  CUSUM and chi-squared attack detection of compromised sensors , 2016, 2016 IEEE Conference on Control Applications (CCA).

[24]  Geir E. Dullerud,et al.  Entropy-minimizing mechanism for differential privacy of discrete-time linear feedback systems , 2014, 53rd IEEE Conference on Decision and Control.

[25]  Sreeram Kannan,et al.  Estimating Mutual Information for Discrete-Continuous Mixtures , 2017, NIPS.

[26]  Henrik Sandberg,et al.  Optimal privacy-preserving policy using constrained additive noise to minimize the fisher information , 2017, 2017 IEEE 56th Annual Conference on Decision and Control (CDC).

[27]  Lawrence H. Ozarow,et al.  Wire-tap channel II , 1984, AT&T Bell Laboratories Technical Journal.

[28]  George J. Pappas,et al.  Differentially Private Filtering , 2012, IEEE Transactions on Automatic Control.

[29]  Carlos Murguia,et al.  Characterization of a CUSUM model-based sensor attack detector , 2016, 2016 IEEE 55th Conference on Decision and Control (CDC).

[30]  Carlos Murguia,et al.  On Privacy of Quantized Sensor Measurements through Additive Noise , 2018, 2018 IEEE Conference on Decision and Control (CDC).

[31]  Tamer Basar,et al.  Privacy constrained information processing , 2015, 2015 54th IEEE Conference on Decision and Control (CDC).

[32]  Jie Chen,et al.  Robust Model-Based Fault Diagnosis for Dynamic Systems , 1998, The International Series on Asian Studies in Computer and Information Science.

[33]  K. Watanabe,et al.  Fault diagnosis in nonlinear chemical processes. Part II. Application to a chemical reactor , 1983 .

[34]  H. Vincent Poor,et al.  Smart meter privacy: A utility-privacy framework , 2011, 2011 IEEE International Conference on Smart Grid Communications (SmartGridComm).

[35]  Rolf H. Weber,et al.  Internet of Things - New security and privacy challenges , 2010, Comput. Law Secur. Rev..

[36]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Carlos Murguia,et al.  On model‐based detectors for linear time‐invariant stochastic systems under sensor attacks , 2019, IET Control Theory & Applications.

[38]  Farhad Farokhi,et al.  Privacy-Constrained Communication , 2016 .

[39]  Brian C. Ross.  Mutual Information between Discrete and Continuous Data Sets , 2014, PloS one.

[40]  A. D. Wyner,et al.  The wire-tap channel , 1975, The Bell System Technical Journal.

[41]  Flávio du Pin Calmon,et al.  Privacy against statistical inference , 2012, 2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[42]  Quanyan Zhu,et al.  Coding sensor outputs for injection attacks detection , 2014, 53rd IEEE Conference on Decision and Control.

[43]  E. Yaz.  Linear Matrix Inequalities In System And Control Theory , 1998, Proceedings of the IEEE.

[44]  Nathan van de Wouw,et al.  Reachable Sets of Hidden CPS Sensor Attacks: Analysis and Synthesis Tools , 2017 .

[45]  Fuzhen Zhang.  The Schur complement and its applications , 2005 .

[46]  H. Vincent Poor,et al.  Enabling Data Exchange in Two-Agent Interactive Systems Under Privacy Constraints , 2014, IEEE Journal of Selected Topics in Signal Processing.

[47]  Jane Labadin,et al.  Feature selection based on mutual information , 2015, 2015 9th International Conference on IT in Asia (CITA).