Carmine Cesarano

Office 1524, Level 5

E-Huset, Lindstedtsvägen 3

Stockholm

I am currently a Postdoctoral researcher at KTH Royal Institute of Technology. I received my Ph.D. in Computer Science from University of Naples Federico II.

I work on AI integrity: establishing what an AI system is assembled from, where its artifacts come from, and whether its runtime behavior matches what was declared. My research covers provenance and bills of materials for agentic AI systems, verification of lineage claims about AI artifacts, and reproducibility under non-determinism.

I also work on systems and software security: finding and removing weaknesses in deployed systems, and constraining what they can do at runtime. This ranges from software testing and vulnerability discovery to security hardening such as debloating and secure configuration, as well as runtime enforcement mechanisms including sandboxing and system-call–level policy enforcement.

Contacts/Socials:

cesarano@kth.se
carmine.cesarano2@unina.it
Google Scholar
Linkedin

selected publications

Tech. Report

GoLeash: Mitigating Golang Software Supply Chain Attacks with Runtime Policy Enforcement

Carmine Cesarano, Martin Monperrus, and Roberto Natella

arXiv preprint arXiv:2505.11016, 2025

DOI Bib

@article{cesarano2025goleash,
  title = {GoLeash: Mitigating Golang Software Supply Chain Attacks with Runtime Policy Enforcement},
  author = {Cesarano, Carmine and Monperrus, Martin and Natella, Roberto},
  journal = {arXiv preprint arXiv:2505.11016},
  doi = {10.48550/arXiv.2505.11016},
  year = {2025},
}

Tech. Report

The Grand Software Supply Chain of AI Systems

Carmine Cesarano and Martin Monperrus

arXiv preprint arXiv:2604.27781, 2026

DOI Bib

@article{cesarano2025grand,
  title = {The Grand Software Supply Chain of AI Systems},
  author = {Cesarano, Carmine and Monperrus, Martin},
  journal = {arXiv preprint arXiv:2604.27781},
  doi = {10.48550/arXiv.2604.27781},
  year = {2026},
}