Can LLMs Hack Enterprise Networks? — RCR Report

2026/03/05 by Andreas Happe, Jürgen Cito

paper · doi:10.1145/3800584

Abstract

This is the Replicated Computational Results (RCR) Report for the paper “Can LLMs Hack Enterprise Networks?” The paper empirically investigates the efficacy and effectiveness of different LLMs for penetration-testing enterprise networks, i.e., Microsoft Active Directory Assumed-Breach Simulations. This RCR report describes the artifacts used in the paper, how to create an evaluation setup, and highlights the analysis scripts provided within our prototype.

Citations

• Benchmarking Practices in LLM-driven Offensive Security: Testbeds, Metrics, and Experiment Design
• Can LLMs Hack Enterprise Networks? --- RCR Package
• LLM Cyber Evaluations Don't Capture Real-World Risk

Related

• Can LLMs Hack Enterprise Networks? --- RCR Package
• Pathway to Secure and Trustworthy ZSM for LLMs: Attacks, Defense, and Opportunities
• Hackphyr: A Local Fine-Tuned LLM Agent for Network Security Environments
• On the Surprising Efficacy of LLMs for Penetration-Testing
• LLM Agents can Autonomously Exploit One-day Vulnerabilities