Zobrazeno 1 - 10
of 220
pro vyhledávání: '"Ding, Ni"'
For $\tilde{f}(t) = \exp(\frac{\alpha-1}{\alpha}t)$, this paper proposes a $\tilde{f}$-mean information gain measure. R\'{e}nyi divergence is shown to be the maximum $\tilde{f}$-mean information gain incurred at each elementary event $y$ of channel o
Externí odkaz:
http://arxiv.org/abs/2405.00423
This paper proposes an $\alpha$-leakage measure for $\alpha\in[0,\infty)$ by a cross entropy interpretation of R{\'{e}}nyi entropy. While R\'{e}nyi entropy was originally defined as an $f$-mean for $f(t) = \exp((1-\alpha)t)$, we reveal that it is als
Externí odkaz:
http://arxiv.org/abs/2401.15202
Autor:
Ding, Ni
This paper studies how to approximate pufferfish privacy when the adversary's prior belief of the published data is Gaussian distributed. Using Monge's optimal transport plan, we show that $(\epsilon, \delta)$-pufferfish privacy is attained if the ad
Externí odkaz:
http://arxiv.org/abs/2401.12391
This paper investigates lift, the likelihood ratio between the posterior and prior belief about sensitive features in a dataset. Maximum and minimum lifts over sensitive features quantify the adversary's knowledge gain and should be bounded to protec
Externí odkaz:
http://arxiv.org/abs/2303.01017
Publikováno v:
PLoS ONE. 9/16/2024, Vol. 19 Issue 9, p1-12. 12p.
This paper proposes a novel watchdog privatization scheme by generalizing local information privacy (LIP) to enhance data utility. To protect the sensitive features $S$ correlated with some useful data $X$, LIP restricts the lift, the ratio of the po
Externí odkaz:
http://arxiv.org/abs/2205.14549
Autor:
Ding, Ni
Pufferfish privacy achieves $\epsilon$-indistinguishability over a set of secret pairs in the disclosed data. This paper studies how to attain $\epsilon$-pufferfish privacy by exponential mechanism, an additive noise scheme that generalizes the Lapla
Externí odkaz:
http://arxiv.org/abs/2201.07388
This paper is concerned with enhancing data utility in the privacy watchdog method for attaining information-theoretic privacy. For a specific privacy constraint, the watchdog method filters out the high-risk data symbols through applying a uniform d
Externí odkaz:
http://arxiv.org/abs/2110.04724
Autor:
Ding, Ni, Farokhi, Farhad
This paper proposes an operational measure of non-stochastic information leakage to formalize privacy against a brute-force guessing adversary. The information is measured by non-probabilistic uncertainty of uncertain variables, the non-stochastic co
Externí odkaz:
http://arxiv.org/abs/2107.01113
This paper proposes an $\alpha$-lift measure for data privacy and determines the optimal privatization scheme that minimizes the $\alpha$-lift in the watchdog method. To release data $X$ that is correlated with sensitive information $S$, the ratio $l
Externí odkaz:
http://arxiv.org/abs/2101.10551