collaborators

6 papers

cs.CL2026

Dense Contexts Are Hard Contexts: Lexical Density Limits Effective Context in LLMs

Giovanni Dettori, Matteo Boffa, Danilo Giordano +2

Input length and the position of relevant information are widely cited as the primary causes of degraded LLM long-context performance. Here, we study lexical density -- the rate at…

cs.CR2026

Autonomous LLM Agents & CTFs: A Second Look

Youness Bouchari, Matteo Boffa, Marco Mellia +3

Large Language Model (LLM) agents are increasingly proposed to automate offensive security tasks, with recent studies reporting near human-level success rates in Capture-the-Flag (…

cs.CR2026

Improving Generalization on Cybersecurity Tasks with Multi-Modal Contrastive Learning

Jianan Huang, Rodolfo V. Valentim, Luca Vassio +4

The use of ML in cybersecurity has long been impaired by generalization issues: Models that work well in controlled scenarios fail to maintain performance in production. The root c…

cs.CR2026

Towards Agentic Honeynet Configuration

Federico Mirra, Matteo Boffa, Idilio Drago +2

Honeypots are deception systems that emulate vulnerable services to collect threat intelligence. While deploying many honeypots increases the opportunity to observe attacker behavi…

cs.CR2026

CyberSleuth: Autonomous Blue-Team LLM Agent for Web Attack Forensics

Stefano Fumero, Kai Huang, Matteo Boffa +3

Post-mortem analysis of compromised systems is a key aspect of cyber forensics, today a mostly manual, slow, and error-prone task. Agentic AI, i.e., LLM-powered agents, is a promis…

cs.CL2025

Large-Scale Constraint Generation -- Can LLMs Parse Hundreds of Constraints?

Matteo Boffa, Jiaxuan You

Recent research has explored the constrained generation capabilities of Large Language Models (LLMs) when explicitly prompted by few task-specific requirements. In contrast, we int…