Matteo Prandi

According to our database1, Matteo Prandi authored at least 8 papers between 2025 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety.
CoRR, April, 2026

Agentic Microphysics: A Manifesto for Generative AI Safety.
CoRR, April, 2026

Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs.
CoRR, January, 2026

Institutional AI: A Governance Framework for Distributional AGI Safety.
CoRR, January, 2026

From Adversarial Poetry to Adversarial Tales: An Interpretability Research Agenda.
CoRR, January, 2026

2025
Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions.
CoRR, December, 2025

Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models.
CoRR, November, 2025

Bench-2-CoP: Can We Trust Benchmarking for EU AI Compliance?
CoRR, August, 2025


  Loading...