collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

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…

cs.CL2026

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…

cs.CL2026

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…

cs.CL2026

Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection

Francesco Giarrusso, Olga E. Sorokoletova, Vincenzo Suriani +1

Jailbreaking techniques pose a significant threat to the safety of Large Language Models (LLMs). Existing defenses typically focus on single-turn attacks, lack coverage across lang…

cs.CL2026

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…

cs.CL2026

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…