Policy advice and best practices on bias and fairness in AI

JM Alvarez, AB Colmenarejo, A Elobaid… - Ethics and Information …, 2024 - Springer
The literature addressing bias and fairness in AI models (fair-AI) is growing at a fast pace,
making it difficult for novel researchers and practitioners to have a bird's-eye view picture of …

The SPATIAL architecture: Design and development experiences from gauging and monitoring the ai inference capabilities of modern applications

AR Ottun, R Marasinghe, T Elemosho… - 2024 IEEE 44th …, 2024 - ieeexplore.ieee.org
Despite its enormous economical and societal impact, lack of human-perceived control and
safety is re-defining the design and development of emerging AI-based technologies. New …

Certifying Accuracy, Privacy, and Robustness of ML-Based Malware Detection

N Bena, M Anisetti, G Gianini, CA Ardagna - SN Computer Science, 2024 - Springer
Recent advances in artificial intelligence (AI) are radically changing how systems and
applications are designed and developed. In this context, new requirements and regulations …

Data management for continuous learning in EHR systems

V Bellandi, P Ceravolo, J Maggesi… - ACM Transactions on …, 2024 - dl.acm.org
To gain a comprehensive understanding of a patient's health, advanced analytics must be
applied to the data collected by electronic health record (EHR) systems. However, managing …

Continuous Management of Machine Learning-Based Application Behavior

M Anisetti, CA Ardagna, N Bena… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Modern applications are increasingly driven by Machine Learning (ML) models whose non-
deterministic behavior is affecting the entire application life cycle from design to operation …

Data Poisoning Attacks and Mitigation Strategies on Federated Support Vector Machines

IJ Mouri, M Ridowan, MA Adnan - SN Computer Science, 2024 - Springer
Federated learning is a machine learning approach where multiple edge devices, each
holding local data samples, send a locally trained model to the central server, and the …

Managing ML-Based Application Non-Functional Behavior: A Multi-Model Approach

M Anisetti, CA Ardagna, N Bena, E Damiani… - arXiv preprint arXiv …, 2023 - arxiv.org
Modern applications are increasingly driven by Machine Learning (ML) models whose non-
deterministic behavior is affecting the entire application life cycle from design to operation …

Beyond Cloud Service Certification

M Anisetti, CA Ardagna, E Damiani… - A Journey into Security …, 2024 - Springer
Cloud computing has been a driving force for many technological innovations and
transformations in various domains and industries. It offers scalable and cost-effective …

[PDF][PDF] A Transparent Certification Scheme Based on Blockchain for Service-Based Systems

N Bena, M Pedrinazzi, M Anisetti… - … Conference on Web …, 2024 - perso.liris.cnrs.fr
Modern service-based systems are characterized by applications composed of
heterogeneous services provided by multiple, untrusted providers, and deployed along the …