Autopentest-drl |top| Site

AutoPentest-DRL is an automated penetration testing framework that uses Deep Reinforcement Learning (DRL) to plan and execute attack paths on computer networks. It was developed by the Cyber Range Organization and Design (CROND) Japan Advanced Institute of Science and Technology (JAIST) Framework Overview

Comparison with LLM-Based Pentesting (e.g., PentestGPT)

Run a Logical Attack:

Test it on a sample topology with a single command: python3 ./AutoPentest-DRL.py logical_attack Use code with caution. Copied to clipboard autopentest-drl

[Reconnaissance] → [Attack Planner (DRL Agent)] → [Exploit Executor] → [State Tracker] ↑ | └─────────────────── Reward Signal ────────────────────────┘ Recent work integrates and attention mechanisms to generate

SHAP values

Cybersecurity professionals distrust "black box" agents that can’t explain their decisions. Recent work integrates and attention mechanisms to generate human-readable attack graphs. A key research direction is Explainable Autopentest-DRL (X-DRL) . Attack Graph Generation (MulVAL):

Artificial Intelligence for Cybersecurity Education and Training : This paper introduces the AutoPentest-DRL

The framework uses Nmap to scan a real target network, identifying its topology and active vulnerabilities. Attack Graph Generation (MulVAL):