article · IEEE Transactions on Information Theory · 2023
Pointwise Maximal Leakage
Sara Saeidian, Giulia Cervia, Tobias J. Oechtering, Mikael Skoglund
Cited by 22Abstract and details only
Abstract
We introduce a privacy measure called pointwise maximal leakage, generalizing the pre-existing notion of maximal leakage, which quantifies the amount of information leaking about a secret <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$X$ </tex-math></inline-formula> by disclosing a single outcome of a (randomized) function calculated on <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$X$ </tex-math></inline-formula> . Pointwise maximal leakage is a robust and operationally meaningful privacy measure that captures the largest amount of information leaking about <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$X$ </tex-math></inline-formula> to adversaries seeking to guess arbitrary (possibly randomized) functions of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$X$ </tex-math></inline-formula> , or equivalently, aiming to maximize arbitrary gain functions. We study several properties of pointwise maximal leakage, e.g., how it composes over multiple outcomes, how it is affected by pre- and post-processing, etc. Furthermore, we propose to view information leakage as a random variable which, in turn, allows us to regard privacy guarantees as requirements imposed on different statistical properties of the information leakage random variable. We define several privacy guarantees and study how they behave under pre-processing, post-processing and composition. Finally, we examine the relationship between pointwise maximal leakage and other privacy notions such as local differential privacy, local information privacy, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$f$ </tex-math></inline-formula> -information, and so on. Overall, our paper constructs a robust and flexible framework for privacy risk assessment whose central notion has a strong operational meaning which can be adapted to a variety of applications and practical scenarios.
Cite this paper
Saeidian, S., Cervia, G., Oechtering, T. J., & Skoglund, M. (2023). Pointwise Maximal Leakage. IEEE Transactions on Information Theory, 69(12), 8054–8080. https://doi.org/10.1109/tit.2023.3304378
Saeidian, Sara, et al. “Pointwise Maximal Leakage.” IEEE Transactions on Information Theory, vol. 69, no. 12, 2023, pp. 8054–80, https://doi.org/10.1109/tit.2023.3304378.
Saeidian, Sara, Giulia Cervia, Tobias J. Oechtering, and Mikael Skoglund. 2023. “Pointwise Maximal Leakage.” IEEE Transactions on Information Theory 69 (12): 8054–80. https://doi.org/10.1109/tit.2023.3304378.
Saeidian, S. et al. (2023) ‘Pointwise Maximal Leakage’, IEEE Transactions on Information Theory, 69(12), pp. 8054–8080. Available at: https://doi.org/10.1109/tit.2023.3304378.
@article{saeidian2023pointwise,
title = {{Pointwise Maximal Leakage}},
author = {Saeidian, Sara and Cervia, Giulia and Oechtering, Tobias J. and Skoglund, Mikael},
journal = {IEEE Transactions on Information Theory},
volume = {69},
number = {12},
pages = {8054--8080},
year = {2023},
doi = {10.1109/tit.2023.3304378}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.