Home
Fabio Massimo Zennaro's picture

Fabio Massimo Zennaro

Associate Professor, Machine Learning
  • E-mailfabio.zennaro@uib.no
  • Visitor Address
    HIB - Thormøhlens gate 55
    5006 Bergen
    Room 
    603N3
  • Postal Address
    Postboks 7803
    5020 Bergen

I am professor in machine learning with interest and experience in different areas of ML.

My current research focuses on structural causal models and causal abstraction. I am interested in understanding how multiple causal models at different levels of abstraction can be related to each other. My reseach in this area ranges from theoretical studies aimed at formally defining and characterizing forms of abstraction to methodological work concerned with learning relationships of abstraction from data and exploiting them in real-world settings.

Previously, I worked on applications of reinforcement learning and Bayesian models to computer security, theoretical analysis of unsupervised algorithms via bounds and information-theoretic methods, evaluation of societal aspects of machine learning, fairness in data aggregation.

I am generally interested in the systematization of machine learning, and its intersections with other fields.

Academic article
  • Show author(s) (2023). Simulating all archetypes of SQL injection vulnerability exploitation using reinforcement learning agents. International Journal of Information Security.
  • Show author(s) (2023). Modelling penetration testing with reinforcement learning using capture-the-flag challenges: Trade-offs between model-free learning and a priori knowledge. IET Information Security.
  • Show author(s) (2021). The Agent Web Model - Modelling web hacking for reinforcement learning. International Journal of Information Security. 17 pages.
  • Show author(s) (2021). Simulating SQL injection vulnerability exploitation using Q-learning reinforcement learning agents. Journal of Information Security and Applications.
  • Show author(s) (2021). A new decision making model based on Rank Centrality for GDM with fuzzy preference relations. European Journal of Operational Research. 1030-1041.
  • Show author(s) (2019). Counterfactually Fair Prediction Using Multiple Causal Models. Lecture Notes in Computer Science (LNCS). 249-266.
  • Show author(s) (2019). An empirical evaluation of the approximation of subjective logic operators using Monte Carlo simulations. International Journal of Approximate Reasoning. 56-77.
  • Show author(s) (2018). Towards understanding sparse filtering: A theoretical perspective. Neural Networks. 154-177.
Academic lecture
  • Show author(s) (2020). Firearm Detection via Convolutional Neural Networks: Comparing a Semantic Segmentation Model Against End-to-End Solutions.
  • Show author(s) (2020). A Left Realist Critique of the Political Value of Adopting Machine Learning Systems in Criminal Justice.
  • Show author(s) (2019). Firearm Detection and Segmentation using an Ensemble of Semantic Neural Networks.
  • Show author(s) (2019). Analyzing and Storing Network Intrusion Detection Data using Bayesian Coresets: A Preliminary Study in Offline and Streaming Settings.
  • Show author(s) (2018). Pooling of Causal Models under Counterfactual Fairness via Causal Judgement Aggregation.
  • Show author(s) (2018). Counterfactually Fair Prediction Using Multiple Causal Models.
Academic chapter/article/Conference paper
  • Show author(s) (2020). Using Subjective Logic to Estimate Uncertainty in Multi-Armed Bandit Problems. 12 pages.
  • Show author(s) (2020). Analyzing and Storing Network Intrusion Detection Data Using Bayesian Coresets: A Preliminary Study in Offline and Streaming Settings. 15 pages.

More information in national current research information system (CRIStin)