Zobrazeno 1 - 10
of 14 440
pro vyhledávání: '"Annamalai, A"'
Autor:
Annamalai, Meenatchi Sundaram Muthu Selva, Balle, Borja, De Cristofaro, Emiliano, Hayes, Jamie
Differentially Private Stochastic Gradient Descent (DP-SGD) is a popular method for training machine learning models with formal Differential Privacy (DP) guarantees. As DP-SGD processes the training data in batches, it uses Poisson sub-sampling to s
Externí odkaz:
http://arxiv.org/abs/2411.10614
Publikováno v:
Published in the Proceedings of the 17th ACM Workshop on Artificial Intelligence and Security (AISec 2024), please cite accordingly
Differentially Private Stochastic Gradient Descent (DP-SGD) is a popular iterative algorithm used to train machine learning models while formally guaranteeing the privacy of users. However, the privacy analysis of DP-SGD makes the unrealistic assumpt
Externí odkaz:
http://arxiv.org/abs/2407.06496
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
Autor:
Annamalai, Dhanvarsh, Nandi, Rana
We present two frameworks to infer some of the properties of neutron stars from their electromagnetic radiation and the emission of continuous gravitational waves due to r-mode oscillations. In the first framework, assuming a distance measurement via
Externí odkaz:
http://arxiv.org/abs/2406.13043
Autor:
Annamalai, Dhanvarsh, Pandey, Akshat
We examine Hawking radiation for a Schwarszchild-type black hole in Starobinsky Bel Robinson (SBR) gravity and calculate the corrected Hawking Temperature using the tunnelling method. We then discuss the deviation of our Hawking temperature from the
Externí odkaz:
http://arxiv.org/abs/2406.09006
This paper presents an auditing procedure for the Differentially Private Stochastic Gradient Descent (DP-SGD) algorithm in the black-box threat model that is substantially tighter than prior work. The main intuition is to craft worst-case initial mod
Externí odkaz:
http://arxiv.org/abs/2405.14106
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
Bio-inspired Address Event Representation (AER) sensors have attracted significant popularity owing to their low power consumption, high sparsity, and high temporal resolution. Spiking Neural Network (SNN) has become the inherent choice for AER data
Externí odkaz:
http://arxiv.org/abs/2402.10078
Publikováno v:
Asian Association of Open Universities Journal, 2024, Vol. 19, Issue 3, pp. 247-263.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/AAOUJ-08-2023-0100
Publikováno v:
Journal of Clinical and Diagnostic Research, Vol 18, Iss 11, Pp 01-06 (2024)
Introduction: Transgender refers to an individual whose gender identity differs from the sex that was assigned at birth. Transgender women (MtF) were assigned male at birth but later recognised themselves as female. The length of the index finger (2D
Externí odkaz:
https://doaj.org/article/32bf5dc96ea445a9a52026b4318a1958