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 research 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.

Conference lecture

• Alexander Egiazarov; Vasileios Mavroeidis; Kamer Vishi et al. (2019). Firearm Detection and Segmentation using an Ensemble of Semantic Neural Networks. (external link)
• Fabio Massimo Zennaro (2019). Analyzing and Storing Network Intrusion Detection Data using Bayesian Coresets: A Preliminary Study in Offline and Streaming Settings. (external link)
• Fabio Massimo Zennaro (2020). A Left Realist Critique of the Political Value of Adopting Machine Learning Systems in Criminal Justice. (external link)
• Alexander Egiazarov; Fabio Massimo Zennaro; Vasileios Mavroeidis (2020). Firearm Detection via Convolutional Neural Networks: Comparing a Semantic Segmentation Model Against End-to-End Solutions. (external link)
• Fabio Massimo Zennaro; Magdalena Ivanovska (2018). Pooling of Causal Models under Counterfactual Fairness via Causal Judgement Aggregation. (external link)

Academic article

• Laszlo Erdodi; Fabio Massimo Zennaro (2021). The Agent Web Model - Modelling web hacking for reinforcement learning. (external link)
• Fabio Massimo Zennaro; Magdalena Ivanovska; Audun Jøsang (2019). An empirical evaluation of the approximation of subjective logic operators using Monte Carlo simulations. (external link)
• Fabio Massimo Zennaro; Magdalena Ivanovska (2018). Counterfactually Fair Prediction Using Multiple Causal Models. (external link)
• Willem Theodorus Schooltink; Fabio Massimo Zennaro (2025). Aligning Graphical and Functional Causal Abstractions. (external link)
• Fabio Massimo Zennaro; Magdalena Ivanovska (2019). Counterfactually Fair Prediction Using Multiple Causal Models. (external link)
• Fabio Massimo Zennaro; Laszlo Tibor Erdodi (2023). Modelling penetration testing with reinforcement learning using capture-the-flag challenges: Trade-offs between model-free learning and a priori knowledge. (external link)
• Jarl Giske; Magda L. Dumitru; Katja Enberg et al. (2025). Premises for digital twins reporting on Atlantic salmon wellbeing. (external link)
• Yorgos Felekis; Fabio Massimo Zennaro; Nicola Branchini et al. (2024). Causal Optimal Transport of Abstractions. (external link)
• D'Acunto, Gabriele; Fabio Massimo Zennaro; Felekis, Yorgos et al. (2025). Causal Abstraction Learning based on the Semantic Embedding Principle. (external link)
• Fabio Massimo Zennaro; Ke Chen (2018). Towards understanding sparse filtering: A theoretical perspective. (external link)
• Fabio Massimo Zennaro; Nicholas George Bishop; Joel Dyer et al. (2024). Causally Abstracted Multi-armed Bandits. (external link)
• Anis Yazidi; Magdalena Ivanovska; Fabio Massimo Zennaro et al. (2021). A new decision making model based on Rank Centrality for GDM with fuzzy preference relations. (external link)
• Åvald Åslaugson Sommervoll; Laszlo Tibor Erdodi; Fabio Massimo Zennaro (2023). Simulating all archetypes of SQL injection vulnerability exploitation using reinforcement learning agents. (external link)
• Joel Dyer; Nicholas George Bishop; Yorgos Felekis et al. (2024). Interventionally Consistent Surrogates for Complex Simulation Models. (external link)
• Laszlo Erdodi; Åvald Åslaugson Sommervoll; Fabio Massimo Zennaro (2021). Simulating SQL injection vulnerability exploitation using Q-learning reinforcement learning agents. (external link)

Academic book chapter

• Ryan Anthony Marinelli; Laszlo Tibor Erdodi; Åvald Åslaugson Sommervoll et al. (2024). Extending Q-Learning Agents in SQLi Environments. (external link)
• Fabio Massimo Zennaro; Audun Jøsang (2020). Using Subjective Logic to Estimate Uncertainty in Multi-Armed Bandit Problems. (external link)
• Fabio Massimo Zennaro (2020). Analyzing and Storing Network Intrusion Detection Data Using Bayesian Coresets: A Preliminary Study in Offline and Streaming Settings. (external link)

Conference poster

• Ryan Anthony Marinelli; Laszlo Tibor Erdodi; Åvald Åslaugson Sommervoll et al. (2024). Function Approximation Techniques to Empower Complex Agents for SQLi. (external link)

See a complete overview of publications in Cristin.