Zobrazeno 1 - 10
of 1 335
pro vyhledávání: '"Palamidessi A."'
Autor:
Biswas, Sayan, Dras, Mark, Faustini, Pedro, Fernandes, Natasha, McIver, Annabelle, Palamidessi, Catuscia, Sadeghi, Parastoo
Within the machine learning community, reconstruction attacks are a principal attack of concern and have been identified even in federated learning, which was designed with privacy preservation in mind. In federated learning, it has been shown that a
Externí odkaz:
http://arxiv.org/abs/2406.13569
Machine learning (ML) algorithms rely primarily on the availability of training data, and, depending on the domain, these data may include sensitive information about the data providers, thus leading to significant privacy issues. Differential privac
Externí odkaz:
http://arxiv.org/abs/2405.14725
Autor:
Makhlouf, Karima, Arcolezi, Heber H., Zhioua, Sami, Brahim, Ghassen Ben, Palamidessi, Catuscia
Automated decision systems are increasingly used to make consequential decisions in people's lives. Due to the sensitivity of the manipulated data as well as the resulting decisions, several ethical concerns need to be addressed for the appropriate u
Externí odkaz:
http://arxiv.org/abs/2312.04404
Autor:
Binkytė, Rūta, Pinzón, Carlos, Lestyán, Szilvia, Jung, Kangsoo, Arcolezi, Héber H., Palamidessi, Catuscia
Differential privacy is a widely adopted framework designed to safeguard the sensitive information of data providers within a data set. It is based on the application of controlled noise at the interface between the server that stores and processes t
Externí odkaz:
http://arxiv.org/abs/2311.04037
Training differentially private machine learning models requires constraining an individual's contribution to the optimization process. This is achieved by clipping the $2$-norm of their gradient at a predetermined threshold prior to averaging and ba
Externí odkaz:
http://arxiv.org/abs/2310.00829
Federated learning (FL) is a framework for training machine learning models in a distributed and collaborative manner. During training, a set of participating clients process their data stored locally, sharing only the model updates obtained by minim
Externí odkaz:
http://arxiv.org/abs/2309.00416
This paper investigates the utility gain of using Iterative Bayesian Update (IBU) for private discrete distribution estimation using data obfuscated with Locally Differentially Private (LDP) mechanisms. We compare the performance of IBU to Matrix Inv
Externí odkaz:
http://arxiv.org/abs/2307.07744
We consider the problem of unfair discrimination between two groups and propose a pre-processing method to achieve fairness. Corrective methods like statistical parity usually lead to bad accuracy and do not really achieve fairness in situations wher
Externí odkaz:
http://arxiv.org/abs/2307.02891
Local differential privacy (LDP) is a variant of differential privacy (DP) that avoids the need for a trusted central curator, at the cost of a worse trade-off between privacy and utility. The shuffle model is a way to provide greater anonymity to us
Externí odkaz:
http://arxiv.org/abs/2305.13075
In recent years, Local Differential Privacy (LDP), a robust privacy-preserving methodology, has gained widespread adoption in real-world applications. With LDP, users can perturb their data on their devices before sending it out for analysis. However
Externí odkaz:
http://arxiv.org/abs/2304.12845