: A Vulnerability Testing Benchmark for Generative Agents
Luca Gioacchini, Alexander Delsanto, Marco Mellia et al.
· 0 citations
3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
AI-Driven Filtering for Role-Based Access
ARBITER is introduced, a system designed to provide RBAC in RAG systems that uses LLMs operating in few-shot settings with prompt-based steering for rapid deployment and role updates, and shows results close to traditional RBAC solutions.
Michele Lorenzo, I. Drago, Dario Salvadori et al.
· 0 citations
Preprint
Sep 2026
AgentLSD: Evaluating AI Security Agents Under Adversarial Task Contamination
AI agents for security inspect web pages, source code, logs, configuration files, and command outputs. These environments may contain deceptive artifacts that influence the agent's behavior. We call this adversarial task contamination. Whereas prompt injection relies on attacker-supplied instructions, task contaminatio...
Matteo Golinelli, I. Drago, Matteo Boffa et al.
· 0 citations