An overview of information-theoretic security and privacy: Metrics, limits and applications
This tutorial reviews fundamental contributions to information security. An integrative
viewpoint is taken that explains the security metrics, including secrecy, privacy, and others …
viewpoint is taken that explains the security metrics, including secrecy, privacy, and others …
Review of results on smart‐meter privacy by data manipulation, demand shaping, and load scheduling
F Farokhi - IET Smart Grid, 2020 - Wiley Online Library
Simple analysis of energy consumption patterns recorded by smart meters can be used to
deduce household occupancy. With access to higher‐resolution smart‐meter readings, we …
deduce household occupancy. With access to higher‐resolution smart‐meter readings, we …
No free lunch theorem for security and utility in federated learning
In a federated learning scenario where multiple parties jointly learn a model from their
respective data, there exist two conflicting goals for the choice of appropriate algorithms. On …
respective data, there exist two conflicting goals for the choice of appropriate algorithms. On …
Generalization bounds: Perspectives from information theory and PAC-Bayes
A fundamental question in theoretical machine learning is generalization. Over the past
decades, the PAC-Bayesian approach has been established as a flexible framework to …
decades, the PAC-Bayesian approach has been established as a flexible framework to …
Visual privacy attacks and defenses in deep learning: a survey
The concerns on visual privacy have been increasingly raised along with the dramatic
growth in image and video capture and sharing. Meanwhile, with the recent breakthrough in …
growth in image and video capture and sharing. Meanwhile, with the recent breakthrough in …
Privacy-preserving aggregate mobility data release: An information-theoretic deep reinforcement learning approach
It is crucial to protect users' location traces against inference attacks on aggregate mobility
data collected from multiple users in various real-world applications. Most of the existing …
data collected from multiple users in various real-world applications. Most of the existing …
Generalization Error Bounds via Rényi-, f-Divergences and Maximal Leakage
In this work, the probability of an event under some joint distribution is bounded by
measuring it with the product of the marginals instead (which is typically easier to analyze) …
measuring it with the product of the marginals instead (which is typically easier to analyze) …
Generalization bounds via information density and conditional information density
F Hellström, G Durisi - IEEE Journal on Selected Areas in …, 2020 - ieeexplore.ieee.org
We present a general approach, based on an exponential inequality, to derive bounds on
the generalization error of randomized learning algorithms. Using this approach, we provide …
the generalization error of randomized learning algorithms. Using this approach, we provide …
Tunable measures for information leakage and applications to privacy-utility tradeoffs
We introduce a tunable measure for information leakage called maximal-leakage. This
measure quantifies the maximal gain of an adversary in inferring any (potentially random) …
measure quantifies the maximal gain of an adversary in inferring any (potentially random) …
Formal security proofs via Doeblin coefficients: optimal side-channel factorization from noisy leakage to random probing
Masking is one of the most popular countermeasures to side-channel attacks, because it can
offer provable security. However, depending on the adversary's model, useful security …
offer provable security. However, depending on the adversary's model, useful security …