Zobrazeno 1 - 10
of 560
pro vyhledávání: '"Ganev, P."'
Autor:
Ganev, Georgi
In this paper, we argue that similarity-based privacy metrics cannot ensure regulatory compliance of synthetic data. Our analysis and counter-examples show that they do not protect against singling out and linkability and, among other fundamental iss
Externí odkaz:
http://arxiv.org/abs/2407.16929
Autor:
Ganev, H. G.
Symplectic symmetry approach to clustering (SSAC) in atomic nuclei, recently proposed, is modified and further developed in more detail. It is firstly applied to the light two-cluster $^{20}$Ne + $\alpha$ system of $^{24}$Mg, the latter exhibiting we
Externí odkaz:
http://arxiv.org/abs/2406.14730
Synthetic data created by differentially private (DP) generative models is increasingly used in real-world settings. In this context, PATE-GAN has emerged as a popular algorithm, combining Generative Adversarial Networks (GANs) with the private train
Externí odkaz:
http://arxiv.org/abs/2406.13985
Differentially private synthetic data generation (DP-SDG) algorithms are used to release datasets that are structurally and statistically similar to sensitive data while providing formal bounds on the information they leak. However, bugs in algorithm
Externí odkaz:
http://arxiv.org/abs/2405.10994
Autor:
Ganev, H. G.
Publikováno v:
Commun. Theor. Phys. 76, 085301 (2024)
The structure of the irreducible collective spaces of the group $Sp(12,R)$, which many-particle nuclear states are classified according to the chain $Sp(12,R) \supset U(6) \supset SO(6) \supset SU_{pn}(3) \otimes SO(2) \supset SO(3)$ of the proton-ne
Externí odkaz:
http://arxiv.org/abs/2401.01649
Autor:
Ganev, Georgi, De Cristofaro, Emiliano
Generative models producing synthetic data are meant to provide a privacy-friendly approach to releasing data. However, their privacy guarantees are only considered robust when models satisfy Differential Privacy (DP). Alas, this is not a ubiquitous
Externí odkaz:
http://arxiv.org/abs/2312.05114
Autor:
Arthur, Lauren, Costello, Jason, Hardy, Jonathan, O'Brien, Will, Rea, James, Rees, Gareth, Ganev, Georgi
Generative AI technologies are gaining unprecedented popularity, causing a mix of excitement and apprehension through their remarkable capabilities. In this paper, we study the challenges associated with deploying synthetic data, a subfield of Genera
Externí odkaz:
http://arxiv.org/abs/2307.04208
Autor:
Ganev, Georgi
In this paper, we argue that synthetic data produced by Differentially Private generative models can be sufficiently anonymized and, therefore, anonymous data and regulatory compliant.
Comment: Accepted to the 1st Workshop on Generative AI and L
Comment: Accepted to the 1st Workshop on Generative AI and L
Externí odkaz:
http://arxiv.org/abs/2307.00359
Generative models trained with Differential Privacy (DP) can produce synthetic data while reducing privacy risks. However, navigating their privacy-utility tradeoffs makes finding the best models for specific settings/tasks challenging. This paper br
Externí odkaz:
http://arxiv.org/abs/2305.10994
Autor:
Ganev, H. G.
Publikováno v:
Int. J. At. Nucl. Phys. 6(1), 027 (2021)
A new symplectic-based shell-model approach to clustering in atomic nuclei is proposed by considering the simple system $^{20}$Ne. Its relation to the collective excitations of this system is mentioned as well. The construction of the Pauli allowed H
Externí odkaz:
http://arxiv.org/abs/2212.04337