The main objective of this project is to design and empirically evaluate algorithms that enable trustworthy and formally verifiable machine learning, with particular emphasis on security and privacy. The research project is structured around two main directions: (1) the development of privacy-preserving machine learning methodologies that reduce or prevent information leakage from training data, and (2) the design and implementation of verifiable mechanisms for enforcing security and privacy guaranties throughout the machine learning lifecycle. Achieving these goals requires large-scale empirical studies with deep neural networks, including transformer architectures and high-dimensional representation models. The research will involve repeated training, different threat models, and extensive hyperparameter searches to ensure statistically sound conclusions. GPU resources are therefore essential for fast training, scalable distributed experiments, and reproducible evaluations. High-performance computing infrastructure will enable systematic analyses that would otherwise be prohibitively expensive. Expected outcomes include novel algorithms, thorough empirical benchmarks, and practical guidelines for building trustworthy ML systems. The project will advance scientific understanding of ML security and privacy and support deployable techniques for real-world use. Results will be shared through peer-reviewed publications, open-source implementations when appropriate, and active engagement with the research community.