2 citations · 3 across the 13 of their papers we have counts for
14 papers
Xeno-Interpretability: Investigating the Alien Minds of LLMs
F. Pierucci, M. Bracale Syrnikov, M. Prandi +3
Large language models are usually interpreted through concepts that humans already possess: truthfulness, refusal, deception, personality, harmfulness, and related categories. This…
Draining the Energy Commons: Self-Defeating Over-Appropriation as a Coordination Failure in Agentic LLM Collectives
Marcantonio Bracale Syrnikov, Federico Pierucci, Matteo Prandi +4
LLMs are increasingly deployed as agents that plan, use tools, and act over time. When they share persistent resources, such as compute pools or energy reserves, decisions by one a…
Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety
Piercosma Bisconti, Matteo Prandi, Federico Pierucci +11
Background. Traditional safety benchmarks for language models evaluate generated text: whether a model outputs toxic language, reproduces bias, or follows harmful instructions. Whe…
Metaphor Is Not All Attention Needs
Olga Sorokoletova, Francesco Giarrusso, Giacomo De Luca +6
Large language models are increasingly deployed in safety-critical applications, where their ability to resist harmful instructions is essential. Although post-training aims to mak…
Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety
Marcello Galisai, Susanna Cifani, Francesco Giarrusso +5
The Adversarial Humanities Benchmark (AHB) evaluates whether model safety refusals survive a shift away from familiar harmful prompt forms. Starting from harmful tasks drawn from M…
Agentic Microphysics: A Manifesto for Generative AI Safety
Federico Pierucci, Matteo Prandi, Marcantonio Bracale Syrnikov +2
This paper advances a methodological proposal for safety research in agentic AI. As systems acquire planning, memory, tool use, persistent identity, and sustained interaction, safe…
AI Agents Under EU Law
Luca Nannini, Adam Leon Smith, Michele Joshua Maggini +6
AI agents - i.e. AI systems that autonomously plan, invoke external tools, and execute multi-step action chains with reduced human involvement - are being deployed at scale across…
Standards for trustworthy AI in the European Union: technical rationale, structural challenges, and an implementation path
Piercosma Bisconti, Marcello Galisai
This white paper examines the technical foundations of European AI standardization under the AI Act. It explains how harmonized standards enable the presumption of conformity mecha…
Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphs
Marcantonio Bracale Syrnikov, Federico Pierucci, Marcello Galisai +6
Multi-agent LLM ensembles can converge on coordinated, socially harmful equilibria. This paper advances an experimental framework for evaluating Institutional AI, our system-level…
Institutional AI: A Governance Framework for Distributional AGI Safety
Federico Pierucci, Marcello Galisai, Marcantonio Syrnikov Bracale +6
As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but m…
From Adversarial Poetry to Adversarial Tales: An Interpretability Research Agenda
Piercosma Bisconti, Marcello Galisai, Matteo Prandi +6
Safety mechanisms in LLMs remain vulnerable to attacks that reframe harmful requests through culturally coded structures. We introduce Adversarial Tales, a jailbreak technique that…
Beyond Single-Agent Safety: A Taxonomy of Risks in LLM-to-LLM Interactions
Piercosma Bisconti, Marcello Galisai, Federico Pierucci +2
This paper examines why safety mechanisms designed for human-model interaction do not scale to environments where large language models (LLMs) interact with each other. Most curren…
Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models
Piercosma Bisconti, Matteo Prandi, Federico Pierucci +7
We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for Large Language Models (LLMs). Across 25 frontier proprietary and open-weigh…
Bench-2-CoP: Can We Trust Benchmarking for EU AI Compliance?
Matteo Prandi, Vincenzo Suriani, Federico Pierucci +3
The rapid advancement of General Purpose AI (GPAI) models necessitates robust evaluation frameworks, especially with emerging regulations like the EU AI Act and its associated Code…