Research focus
Sapienza University of Rome, GLADIA LabRome, Italy
Adversarial Attacks in LLMs
AI Safety
Adversarial Attacks
Interpretability
Latest publications
A preview of approved public publications linked to this researcher.
- Open
Steering Vectors are an Adversarial Attack Surface
arXiv (Cornell University) - 2026 - OpenAlex00 OpenAlex citations
Regional connection
DSML member