This research aims to support engineers across the entire Software Development Life Cycle (SDLC) through AI-based platforms and environments powered by Large Language Models (LLMs), enabling secure and trustworthy analysis, design, and development of AI-based software systems.

It also addresses challenges such as hallucinations, biases, data privacy risks, and code vulnerabilities via tools like prompt vulnerability detectors, SBOM analysers, and static/dynamic code analysers.

Selected Publications

Al-Obeidallah, M., Piras, L., Iloanugo, O., Mouratidis, H., Alkubaisy, D. and Dellagiacoma, D.: Goal-modeling privacy-by-design patterns for supporting GDPR compliance. In Proceedings of the 18th International Conference on Software Technologies (ICSOFT), 2023.

Piras, L. et al. “DEFeND DSM: A Data Scope Management Service for Model-Based Privacy by Design GDPR Compliance” in Int. Conf. on Trust, Privacy and Security in Digital Business (TrustBus). Springer, 2020.

Thiha, M., Yetgin, H., Piras, L. and Al-Obeidallah, M.G.: Enhancing Privacy, Censorship Resistance, and User Engagement in a Blockchain-Based Social Network. In 20th International Conference on Evaluation of Novel Approaches to Software Engineering (ENASE). 2025.

Senanayake, J., Kalutarage, H., Al-Kadri, M.O., Petrovski, A. and Piras, L.: Android source code vulnerability detection: a systematic literature review. ACM Computing Surveys Journal, 2023.

Senanayake, J., Kalutarage, H., Piras, L., Al-Kadri, M.O. and Petrovski, A.: Assuring Privacy of AI-Powered Community Driven Android Code Vulnerability Detection. In European Symposium on Research in Computer Security. Springer, 2024a.

Senanayake, J. et al. Defendroid: Real-time Android code vulnerability detection via blockchain federated neural network with XAI. Journal of Information Security and Applications, 2024b.