carried out during my Bachelor's Degree in Applied Computer Science and Artificial Intelligence and Master's Degree in Computer Science (curricula in Artificial Intelligence and Data Science) at Sapienza University of Rome.
Development of a novel graph counterfactual explainer (XAI) that allows for edge additions, deletions and node features perturbations. Extending CF-GNNExplainer (Lucic et al.) and improving over state-of-the-art.
Analysis of impostor attacks on EEG-based authentication systems. Implementation of a CNN Autoencoder model for EEG signal reconstruction and outlier detection to identify unveiled impostor attacks, which are attacks where the users' secret keys are known to the impostors.
Time series forecasting: enhance frequency-domain MLPs (Yi et al., 2023b) by integrating the Dual-Tree Complex Wavelet Transform on non-stationary datasets.
Roofline-analysis workflow for CUDA kernels that simulate a convolutional neural network (CNN) training performed on the Leonardo HPC node proding NVIDIA A100 accelerators.
Seminar on Quantum Machine Learning: theory, architecture and training pipeline of a Quantum Diffudsion Model; based on the Quantum Diffusion Model paper by Giacu et al.
Aligning Minerva to human values with Direct Preference Optimization (DPO) and Kahneman-Tversky Optimization (KTO).
Implementation and analysis of performances of Kolmogorov-Arnold Networks in image classification tasks: full pipeline.
Expert imitation learning for Reinforcement Learning agents using denoising diffusion in Gymnasium environments.
Large-scale deployment of an image-generation diffusion model using AWS Lambda, S3, ECR, EC2, CloudWatch, API Gateway, Docker and Locust.
LLMs and visual robotic navigation in a Webots simulated environment. NAO robot navigation integrating image question answering and captioning.
Survey on Neural Networks poisoning, backdoor attacks and possible mitigations.
Multimodal vehicle driving dashboard developed in a Webots simulated environment integrated with a SUMO interface.
Formal verification of a Reinforcement Learning agent with SPIN to guarantee safe actions execution in Gymnasium environments.
Implementing REINFORCE Algorithm with no use of Deep Learning Libraries.
Prediction of stocks through LSTMs.
Thorough analysis of NBA data and statistics and prediction of future winners.