Preserving privacy and security in federated learning

T Nguyen, MT Thai - IEEE/ACM Transactions on Networking, 2023 - ieeexplore.ieee.org
Federated learning is known to be vulnerable to both security and privacy issues. Existing
research has focused either on preventing poisoning attacks from users or on concealing …

Privacy-preserving explainable AI: a survey

TT Nguyen, TT Huynh, Z Ren, TT Nguyen… - Science China …, 2025 - Springer
As the adoption of explainable AI (XAI) continues to expand, the urgency to address its
privacy implications intensifies. Despite a growing corpus of research in AI privacy and …

A survey of privacy-preserving model explanations: Privacy risks, attacks, and countermeasures

TT Nguyen, TT Huynh, Z Ren, TT Nguyen… - arXiv preprint arXiv …, 2024 - arxiv.org
As the adoption of explainable AI (XAI) continues to expand, the urgency to address its
privacy implications intensifies. Despite a growing corpus of research in AI privacy and …

The privacy-explainability trade-off: unraveling the impacts of differential privacy and federated learning on attribution methods

S Saifullah, D Mercier, A Lucieri, A Dengel… - Frontiers in Artificial …, 2024 - frontiersin.org
Since the advent of deep learning (DL), the field has witnessed a continuous stream of
innovations. However, the translation of these advancements into practical applications has …

SoK: Taming the Triangle--On the Interplays between Fairness, Interpretability and Privacy in Machine Learning

J Ferry, U Aïvodji, S Gambs, MJ Huguet… - arXiv preprint arXiv …, 2023 - arxiv.org
Machine learning techniques are increasingly used for high-stakes decision-making, such
as college admissions, loan attribution or recidivism prediction. Thus, it is crucial to ensure …

Towards a game-theoretic understanding of explanation-based membership inference attacks

K Kumari, M Jadliwala, SK Jha, A Maiti - … on Decision and Game Theory for …, 2024 - Springer
Abstract Model explanations improve the transparency of black-box machine learning (ML)
models and their decisions; however, they can also enable privacy threats like membership …

Addressing ethical issues in healthcare artificial intelligence using a lifecycle-informed process

BX Collins, JC Bélisle-Pipon, BJ Evans… - JAMIA …, 2024 - academic.oup.com
Objectives Artificial intelligence (AI) proceeds through an iterative and evaluative process of
development, use, and refinement which may be characterized as a lifecycle. Within this …

Privacy-Preserving Algorithmic Recourse

S Pentyala, S Sharma, S Kariyappa, F Lecue… - arXiv preprint arXiv …, 2023 - arxiv.org
When individuals are subject to adverse outcomes from machine learning models, providing
a recourse path to help achieve a positive outcome is desirable. Recent work has shown …

Recent Advances in Federated Graph Learning

TR Jeter, MT Thai - Handbook of Trustworthy Federated Learning, 2024 - Springer
Abstract Graph Neural Networks (GNNs) exhibit tremendous potential in addressing graph-
related tasks such as node classification and link prediction. However, training GNNs on …

XSub: Explanation-Driven Adversarial Attack against Blackbox Classifiers via Feature Substitution

K Vu, P Lai, T Nguyen - arXiv preprint arXiv:2409.08919, 2024 - arxiv.org
Despite its significant benefits in enhancing the transparency and trustworthiness of artificial
intelligence (AI) systems, explainable AI (XAI) has yet to reach its full potential in real-world …