2000 character limit reached
List Privacy Under Function Recoverability
Published 11 Jul 2023 in cs.IT and math.IT | (2307.05828v2)
Abstract: For a given function of user data, a querier must recover with at least a prescribed probability, the value of the function based on a user-provided query response. Subject to this requirement, the user forms the query response so as to minimize the likelihood of the querier guessing a list of prescribed size to which the data value belongs based on the query response. We obtain a general converse upper bound for maximum list privacy. This bound is shown to be tight for the case of a binary-valued function through an explicit achievability scheme that involves an add-noise query response.
- S. Asoodeh, M. Diaz, F. Alajaji and T. Linder, “Estimation efficiency under privacy constraints,” IEEE Transactions on Information Theory, vol. 65,6565,65 , no. 3333, pp. 1512151215121512 - 1534153415341534, 2019201920192019.
- R. Bassily, A. Groce, J. Katz and A. Smith, “Coupled-world privacy: Exploiting adversarial uncertainty in statistical data privacy,” in Foundations of Computer Science, pp. 439439439439-448448448448, Oct. 2013201320132013.
- M. Diaz, H. Wang, F. P. Calmon and L. Sankar, “On the robustness of information-theoretic privacy measures and mechanisms,” IEEE Transactions on Information Theory, vol. 66, no. 4, pp. 1949-1978, April 2020.
- C. Dwork, “Differential privacy,” in International Colloquium on Automata, Languages and Programming, pp 1111-12121212, Springer, July 2006200620062006.
- C. Dwork, F. McSherry, K. Nissim and A. Smith, “Calibrating noise to sensitivity in private data analysis,” in Theory of Cryptography Conference, pp. 265265265265-284284284284, Springer, 2006200620062006.
- Q. Geng, W. Ding, R. Guo and S. Kumar, “Tight analysis of privacy and utility tradeoff in approximate differential privacy,” in International Conference on Artificial Intelligence and Statistics, pp. 89-99, 2020.
- Q. Geng and P. Viswanath, “The optimal noise-adding mechanism in differential privacy,” IEEE Transactions on Information Theory, vol. 62,6262,62 , no. 2222, pp. 925925925925-951951951951, Feb. 2016.20162016.2016 .
- M. Hardt and K. Talwar, “On the geometry of differential privacy,” in ACM Symposium on Theory of Computing, pp. 705705705705-714714714714, June 2010201020102010.
- F. du Pin Calmon and N. Fawaz, “Privacy against statistical inference,” in Allerton Conference on Communication, Control and Computing, pp. 1401140114011401-1408140814081408, Oct. 2012201220122012.
- C. Huang, P. Kairouz, X. Chen, L. Sankar and R. Rajagopal, “Context-aware generative adversarial privacy,” Entropy, vol. 19,1919,19 , no. 12121212, Dec. 2017.20172017.2017 .
- S. P. Kasivisiwanathan and A. Smith, “On the semantics of differential privacy: A Bayesian formulation,” Journal of Privacy and Confidentiality, vol. 6666, no. 1111, Aug. 2014201420142014.
- A. Makhdoumi and N. Fawaz, “Privacy-utility tradeoff under statistical uncertainty,”in Allerton Conference on Communication, Control and Computing, pp. 1627162716271627-1634163416341634, 2013201320132013.
- F. McSherry and K. Talwar, “Mechanism design via differential privacy,” in Symposium on Foundations of Computer Science, pp. 94949494-103103103103, Oct. 2007200720072007.
- I. Mironov, “Rényi differential privacy,” in IEEE Computer Security Foundations Symposium, pp. 263-275, 2017.
- A. Nageswaran and P. Narayan, “Data privacy for a ρ𝜌\rhoitalic_ρ-recoverable function,” in IEEE International Symposium on Information Theory, pp. 1046104610461046-1050105010501050, June 2018201820182018.
- A. Nageswaran and P. Narayan, “Data privacy for a ρ𝜌\rhoitalic_ρ-recoverable function,” IEEE Transactions on Information Theory, vol. 65, no. 6, pp. 3470347034703470-3488348834883488, June 2019201920192019.
- A. Nageswaran and P. Narayan, “Predicate privacy and list privacy for a ρ𝜌\rhoitalic_ρ-recoverable function,” in IEEE International Symposium on Information Theory, pp. 2139-2143, July 2019201920192019.
- L. Sankar, S. R. Rajagopalan and H. V. Poor, “Utility-privacy tradeoff in databases: An information-theoretic approach,” IEEE Transactions on Information Forensics and Security, vol. 8888, no. 6666, 2013201320132013.
- C. Schieler and P. Cuff, “The henchman problem: Measuring secrecy by the minimum distortion in a list,” IEEE Transactions on Information Theory, vol. 62,6262,62 , no. 6666, pp. 3436343634363436-3450345034503450, 2016201620162016.
- Y. Wang, S. Aeron, A. S. Rakin, T. Koike-Akino and P. Moulin, “Robust machine learning via privacy/ rate-distortion theory,” in IEEE International Symposium on Information Theory, pp. 1320-1325, 2021.
- L. Wasserman and S. Zhou, “A statistical framework for differential privacy,” Journal of the American Statistical Association, vol. 105105105105, pp. 375375375375-389389389389, 2010201020102010.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
