Research

My research is focused on improving and understanding the trustworthiness of AI architectures in computer vision and cyber-physical systems. This is accomplished by facing safety and security aspects that may threaten the reliability of neural networks (adversarial attacks and defenses, robustness analysis against input perturbations, poisoning attacks, out-of-distribution detection, etc.).

Recent publications

Please visit my Google Scholar and Semantic Scholar for the complete list of publications.

Misc

  • Coordinator of the project “On the Safety and Security of Distributed AI-based Autonomous Multi-Agent Systems” financed by the Department of Excellence in Robotics & AI of Scuola Superiore Sant’Anna Pisa.
  • Reviewer for IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), International Conference of Computer Vision (ICCV2023), IEEE Transactions on Intelligent Transportation Systems (TITS), IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2023), IEEE Transactions on Information Forensics and Security, ACM Transactions on Embedded Computing Systems, RTSS 2022, DAC’21, EMSOFT 2022, and others.

Contact

giulio.rossolini@santannapisa.it

Last update

January 27, 2023