Image de couverture de livre

Bayes' capacity as a measure for reconstruction attacks in federated learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Biswas, Sayan, Dras, Mark, Faustini, Pedro, Fernandes, Natasha, McIver, Annabelle, Palamidessi, Catuscia, Sadeghi, Parastoo
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence Cryptography and Security Information Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Comparing privacy notions for protection against reconstruction attacks in machine learning
par: Biswas, Sayan, et autres
Publié: (2025)

Composition Theorems for f-Differential Privacy
par: Fernandes, Natasha, et autres
Publié: (2025)

Empirical Calibration and Metric Differential Privacy in Language Models
par: Faustini, Pedro, et autres
Publié: (2025)

A Quantitative Information Flow Analysis of the Topics API
par: Alvim, Mário S., et autres
Publié: (2023)

IDT: Dual-Task Adversarial Attacks for Privacy Protection
par: Faustini, Pedro, et autres
Publié: (2024)

Tight Differential Privacy Guarantees for the Shuffle Model with $k$-Randomized Response
par: Biswas, Sayan, et autres
Publié: (2022)

Mitigating Membership Inference Vulnerability in Personalized Federated Learning
par: Jung, Kangsoo, et autres
Publié: (2025)

On the Consistency and Performance of the Iterative Bayesian Update
par: ElSalamouny, Ehab, et autres
Publié: (2025)

Information Leakage Envelopes
par: Saeidian, Sara, et autres
Publié: (2026)

The Privacy-Utility Trade-off in the Topics API
par: Alvim, Mário S., et autres
Publié: (2024)

A privacy preserving querying mechanism with high utility for electric vehicles
par: Atmaca, Ugur Ilker, et autres
Publié: (2022)

Beyond Theoretical Bounds: Empirical Privacy Loss Calibration for Text Rewriting Under Local Differential Privacy
par: Li, Weijun, et autres
Publié: (2026)

Flexible and scalable privacy assessment for very large datasets, with an application to official governmental microdata
par: Alvim, Mário S., et autres
Publié: (2022)

A novel analysis of utility in privacy pipelines, using Kronecker products and quantitative information flow
par: Alvim, Mário S., et autres
Publié: (2023)

Bayes Security: A Not So Average Metric
par: Chatzikokolakis, Konstantinos, et autres
Publié: (2020)

Jeffrey's update rule as a minimizer of Kullback-Leibler divergence
par: Pinzón, Carlos, et autres
Publié: (2025)

Beyond Epsilon: A Principled QIF Framework for Local Differential Privacy
par: Gonze, Ramon G., et autres
Publié: (2026)

Protection against Source Inference Attacks in Federated Learning
par: Athanasiou, Andreas, et autres
Publié: (2026)

Self-Defense: Optimal QIF Solutions and Application to Website Fingerprinting
par: Athanasiou, Andreas, et autres
Publié: (2024)

Protection against Source Inference Attacks in Federated Learning using Unary Encoding and Shuffling
par: Athanasiou, Andreas, et autres
Publié: (2024)

Graded Suspiciousness of Adversarial Texts to Human
par: Tonni, Shakila Mahjabin, et autres
Publié: (2024)

Information Density Bounds for Privacy
par: Saeidian, Sara, et autres
Publié: (2024)

A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Results
par: Makhlouf, Karima, et autres
Publié: (2024)

Generalized Rainbow Differential Privacy
par: Gu, Yuzhou, et autres
Publié: (2023)

Estimating the True Distribution of Data Collected with Randomized Response
par: Pinzón, Carlos Antonio, et autres
Publié: (2026)

A new measure for dynamic leakage based on quantitative information flow
par: Soares, Luigi D. C., et autres
Publié: (2025)

Metric Privacy in Federated Learning for Medical Imaging: Improving Convergence and Preventing Client Inference Attacks
par: Díaz, Judith Sáinz-Pardo, et autres
Publié: (2025)

Effective and secure federated online learning to rank
par: Wang, Shuyi
Publié: (2024)

On the Impact of Multi-dimensional Local Differential Privacy on Fairness
par: Makhlouf, Karima, et autres
Publié: (2023)

Detection of ransomware attacks using federated learning based on the CNN model
par: Nguyen, Hong-Nhung, et autres
Publié: (2024)

Quantifying Privacy via Information Density
par: Grosse, Leonhard, et autres
Publié: (2024)

Causal Discovery Under Local Privacy
par: Binkytė, Rūta, et autres
Publié: (2023)

SoK: Timeline based event reconstruction for digital forensics: Terminology, methodology, and current challenges
par: Breitinger, Frank, et autres
Publié: (2025)

Advancing Recommender Systems by mitigating Shilling attacks
par: Chichani, Aditya, et autres
Publié: (2024)

Local Differential Privacy-Preserving Spectral Clustering for General Graphs
par: Mukherjee, Sayan, et autres
Publié: (2023)

Shadow defense against gradient inversion attack in federated learning
par: Jiang, Le, et autres
Publié: (2025)

DLP: towards active defense against backdoor attacks with decoupled learning process
par: Ying, Zonghao, et autres
Publié: (2024)

Revisiting the attacker's knowledge in inference attacks against Searchable Symmetric Encryption
par: Damie, Marc, et autres
Publié: (2025)

Secure Federated Graph-Filtering for Recommender Systems
par: Nicolas, Julien, et autres
Publié: (2025)

Robust softmax aggregation on blockchain based federated learning with convergence guarantee
par: Wu, Huiyu, et autres
Publié: (2023)