Sökning: "Emiliano Casalicchio"

Hittade 3 avhandlingar innehållade orden Emiliano Casalicchio.

  1. 1. Towards Automated Context-aware Vulnerability Risk Management

    Författare :Vida Ahmadi Mehri; Emiliano Casalicchio; Patrik Arlos; Stefan Axelsson; Blekinge Tekniska Högskola; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Vulnerability Risk Management; VRM; Automated Context-Aware Vulnerability Risk Management; ACVRM; Information security; Computer Science; Datavetenskap;

    Sammanfattning : The information security landscape continually evolves with increasing publicly known vulnerabilities (e.g., 25064 new vulnerabilities in 2022). Vulnerabilities play a prominent role in all types of security related attacks, including ransomware and data breaches. LÄS MER

  3. 2. Resource-Aware and Personalized Federated Learning via Clustering Analysis

    Författare :Ahmed Abbas Mohsin Al-Saedi; Veselka Boeva; Emiliano Casalicchio; György Dán; Blekinge Tekniska Högskola; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Federated Learning; Clustering Analysis; Eccentricity Analysis; Non- IID Data; Model Personalization; Computer Science; Datavetenskap;

    Sammanfattning : Today’s advancement in Artificial Intelligence (AI) enables training Machine Learning (ML) models on the daily-produced data by connected edge devices. To make the most of the data stored on the device, conventional ML approaches require gathering all individual data sets and transferring them to a central location to train a common model. LÄS MER

  4. 3. Energy Efficiency in Machine Learning : Approaches to Sustainable Data Stream Mining

    Författare :Eva García Martín; Håkan Grahn; Veselka Boeva; Emiliano Casalicchio; Jesse Read; Blekinge Tekniska Högskola; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; machine learning; energy efficiency; data stream mining; green machine learning; edge computing; Computer Science; Datavetenskap;

    Sammanfattning : Energy efficiency in machine learning explores how to build machine learning algorithms and models with low computational and power requirements. Although energy consumption is starting to gain interest in the field of machine learning, still the majority of solutions focus on obtaining the highest predictive accuracy, without a clear focus on sustainability. LÄS MER